diff options
Diffstat (limited to 'net')
105 files changed, 1391 insertions, 1426 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 2a739ad..ab2225d 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -382,6 +382,18 @@ static void vlan_sync_address(struct net_device *dev, memcpy(vlan->real_dev_addr, dev->dev_addr, ETH_ALEN); } +static void vlan_transfer_features(struct net_device *dev, + struct net_device *vlandev) +{ + unsigned long old_features = vlandev->features; + + vlandev->features &= ~dev->vlan_features; + vlandev->features |= dev->features & dev->vlan_features; + + if (old_features != vlandev->features) + netdev_features_change(vlandev); +} + static void __vlan_device_event(struct net_device *dev, unsigned long event) { switch (event) { @@ -410,10 +422,8 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, int i, flgs; struct net_device *vlandev; - if (is_vlan_dev(dev)) { + if (is_vlan_dev(dev)) __vlan_device_event(dev, event); - goto out; - } grp = __vlan_find_group(dev); if (!grp) @@ -450,6 +460,18 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, } break; + case NETDEV_FEAT_CHANGE: + /* Propagate device features to underlying device */ + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = vlan_group_get_device(grp, i); + if (!vlandev) + continue; + + vlan_transfer_features(dev, vlandev); + } + + break; + case NETDEV_DOWN: /* Put all VLANs for this dev in the down state too. */ for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index c961f08..5d055c2 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -663,6 +663,8 @@ static int vlan_dev_init(struct net_device *dev) (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); + dev->features |= real_dev->features & real_dev->vlan_features; + /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 9d52ebf..05fafdc 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -188,10 +188,13 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev, return 0; } } - } else { - skb_push(skb, 2); - if (brdev->payload == p_bridged) + } else { /* e_vc */ + if (brdev->payload == p_bridged) { + skb_push(skb, 2); memset(skb->data, 0, 2); + } else { /* p_routed */ + skb_pull(skb, ETH_HLEN); + } } skb_debug(skb); @@ -377,11 +380,8 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) (skb->data + 6, ethertype_ipv4, sizeof(ethertype_ipv4)) == 0) skb->protocol = __constant_htons(ETH_P_IP); - else { - brdev->stats.rx_errors++; - dev_kfree_skb(skb); - return; - } + else + goto error; skb_pull(skb, sizeof(llc_oui_ipv4)); skb_reset_network_header(skb); skb->pkt_type = PACKET_HOST; @@ -394,44 +394,56 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) (memcmp(skb->data, llc_oui_pid_pad, 7) == 0)) { skb_pull(skb, sizeof(llc_oui_pid_pad)); skb->protocol = eth_type_trans(skb, net_dev); - } else { - brdev->stats.rx_errors++; - dev_kfree_skb(skb); - return; - } + } else + goto error; - } else { - /* first 2 chars should be 0 */ - if (*((u16 *) (skb->data)) != 0) { - brdev->stats.rx_errors++; - dev_kfree_skb(skb); - return; + } else { /* e_vc */ + if (brdev->payload == p_routed) { + struct iphdr *iph; + + skb_reset_network_header(skb); + iph = ip_hdr(skb); + if (iph->version == 4) + skb->protocol = __constant_htons(ETH_P_IP); + else if (iph->version == 6) + skb->protocol = __constant_htons(ETH_P_IPV6); + else + goto error; + skb->pkt_type = PACKET_HOST; + } else { /* p_bridged */ + /* first 2 chars should be 0 */ + if (*((u16 *) (skb->data)) != 0) + goto error; + skb_pull(skb, BR2684_PAD_LEN); + skb->protocol = eth_type_trans(skb, net_dev); } - skb_pull(skb, BR2684_PAD_LEN + ETH_HLEN); /* pad, dstmac, srcmac, ethtype */ - skb->protocol = eth_type_trans(skb, net_dev); } #ifdef CONFIG_ATM_BR2684_IPFILTER - if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) { - brdev->stats.rx_dropped++; - dev_kfree_skb(skb); - return; - } + if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) + goto dropped; #endif /* CONFIG_ATM_BR2684_IPFILTER */ skb->dev = net_dev; ATM_SKB(skb)->vcc = atmvcc; /* needed ? */ pr_debug("received packet's protocol: %x\n", ntohs(skb->protocol)); skb_debug(skb); - if (unlikely(!(net_dev->flags & IFF_UP))) { - /* sigh, interface is down */ - brdev->stats.rx_dropped++; - dev_kfree_skb(skb); - return; - } + /* sigh, interface is down? */ + if (unlikely(!(net_dev->flags & IFF_UP))) + goto dropped; brdev->stats.rx_packets++; brdev->stats.rx_bytes += skb->len; memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); netif_rx(skb); + return; + +dropped: + brdev->stats.rx_dropped++; + goto free_skb; +error: + brdev->stats.rx_errors++; +free_skb: + dev_kfree_skb(skb); + return; } /* @@ -518,9 +530,9 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) struct sk_buff *next = skb->next; skb->next = skb->prev = NULL; + br2684_push(atmvcc, skb); BRPRIV(skb->dev)->stats.rx_bytes -= skb->len; BRPRIV(skb->dev)->stats.rx_packets--; - br2684_push(atmvcc, skb); skb = next; } diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index d8f2157..034aa10 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -64,20 +64,15 @@ void ax25_frames_acked(ax25_cb *ax25, unsigned short nr) void ax25_requeue_frames(ax25_cb *ax25) { - struct sk_buff *skb, *skb_prev = NULL; + struct sk_buff *skb; /* * Requeue all the un-ack-ed frames on the output queue to be picked * up by ax25_kick called from the timer. This arrangement handles the * possibility of an empty output queue. */ - while ((skb = skb_dequeue(&ax25->ack_queue)) != NULL) { - if (skb_prev == NULL) - skb_queue_head(&ax25->write_queue, skb); - else - skb_append(skb_prev, skb, &ax25->write_queue); - skb_prev = skb; - } + while ((skb = skb_dequeue_tail(&ax25->ack_queue)) != NULL) + skb_queue_head(&ax25->write_queue, skb); } /* diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index eb62558..0c2c937 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -423,8 +423,8 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) rfcomm_dlc_lock(d); d->state = BT_CLOSED; - rfcomm_dlc_unlock(d); d->state_change(d, err); + rfcomm_dlc_unlock(d); skb_queue_purge(&d->tx_queue); rfcomm_dlc_unlink(d); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index c3f749a..c919187 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -566,11 +566,22 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) if (dlc->state == BT_CLOSED) { if (!dev->tty) { if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { - if (rfcomm_dev_get(dev->id) == NULL) + /* Drop DLC lock here to avoid deadlock + * 1. rfcomm_dev_get will take rfcomm_dev_lock + * but in rfcomm_dev_add there's lock order: + * rfcomm_dev_lock -> dlc lock + * 2. rfcomm_dev_put will deadlock if it's + * the last reference + */ + rfcomm_dlc_unlock(dlc); + if (rfcomm_dev_get(dev->id) == NULL) { + rfcomm_dlc_lock(dlc); return; + } rfcomm_dev_del(dev); rfcomm_dev_put(dev); + rfcomm_dlc_lock(dlc); } } else tty_hangup(dev->tty); diff --git a/net/core/dev.c b/net/core/dev.c index a1607bc..c421a1f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -119,6 +119,7 @@ #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> +#include <linux/if_vlan.h> #include "net-sysfs.h" @@ -903,7 +904,11 @@ int dev_change_name(struct net_device *dev, char *newname) strlcpy(dev->name, newname, IFNAMSIZ); rollback: - device_rename(&dev->dev, dev->name); + err = device_rename(&dev->dev, dev->name); + if (err) { + memcpy(dev->name, oldname, IFNAMSIZ); + return err; + } write_lock_bh(&dev_base_lock); hlist_del(&dev->name_hlist); @@ -1358,6 +1363,29 @@ 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_GEN_CSUM) || + ((features & NETIF_F_IP_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_IPV6_CSUM) && + protocol == htons(ETH_P_IPV6))); +} + +static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) +{ + if (can_checksum_protocol(dev->features, skb->protocol)) + return true; + + if (skb->protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + if (can_checksum_protocol(dev->features & dev->vlan_features, + veh->h_vlan_encapsulated_proto)) + return true; + } + + return false; +} /* * Invalidate hardware checksum when packet is to be mangled, and @@ -1636,14 +1664,8 @@ int dev_queue_xmit(struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_set_transport_header(skb, skb->csum_start - skb_headroom(skb)); - - if (!(dev->features & NETIF_F_GEN_CSUM) && - !((dev->features & NETIF_F_IP_CSUM) && - skb->protocol == htons(ETH_P_IP)) && - !((dev->features & NETIF_F_IPV6_CSUM) && - skb->protocol == htons(ETH_P_IPV6))) - if (skb_checksum_help(skb)) - goto out_kfree_skb; + if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb)) + goto out_kfree_skb; } gso: @@ -2055,6 +2077,10 @@ int netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); + /* Don't receive packets in an exiting network namespace */ + if (!net_alive(dev_net(skb->dev))) + goto out; + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -3137,7 +3163,7 @@ int dev_change_flags(struct net_device *dev, unsigned flags) * Load in the correct multicast list now the flags have changed. */ - if (dev->change_rx_flags && (dev->flags ^ flags) & IFF_MULTICAST) + if (dev->change_rx_flags && (old_flags ^ flags) & IFF_MULTICAST) dev->change_rx_flags(dev, IFF_MULTICAST); dev_set_rx_mode(dev); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5d9d713..65f01f7 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1714,7 +1714,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) return nla_nest_end(skb, nest); nla_put_failure: - return nla_nest_cancel(skb, nest); + nla_nest_cancel(skb, nest); + return -EMSGSIZE; } static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, @@ -2057,9 +2058,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, goto nla_put_failure; } - ci.ndm_used = now - neigh->used; - ci.ndm_confirmed = now - neigh->confirmed; - ci.ndm_updated = now - neigh->updated; + ci.ndm_used = jiffies_to_clock_t(now - neigh->used); + ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); + ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 72b4c18..7c52fe2 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -140,6 +140,9 @@ static void cleanup_net(struct work_struct *work) struct pernet_operations *ops; struct net *net; + /* Be very certain incoming network packets will not find us */ + rcu_barrier(); + net = container_of(work, struct net, work); mutex_lock(&net_mutex); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 8dca211..fdf5377 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -390,6 +390,7 @@ struct pktgen_thread { int cpu; wait_queue_head_t queue; + struct completion start_done; }; #define REMOVE 1 @@ -3414,6 +3415,7 @@ static int pktgen_thread_worker(void *arg) BUG_ON(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); + complete(&t->start_done); pr_debug("pktgen: starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current)); @@ -3615,6 +3617,7 @@ static int __init pktgen_create_thread(int cpu) INIT_LIST_HEAD(&t->if_list); list_add_tail(&t->th_list, &pktgen_threads); + init_completion(&t->start_done); p = kthread_create(pktgen_thread_worker, t, "kpktgend_%d", cpu); if (IS_ERR(p)) { @@ -3639,6 +3642,7 @@ static int __init pktgen_create_thread(int cpu) } wake_up_process(p); + wait_for_completion(&t->start_done); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cf857c4..a9a7721 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -498,7 +498,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) return nla_nest_end(skb, mx); nla_put_failure: - return nla_nest_cancel(skb, mx); + nla_nest_cancel(skb, mx); + return -EMSGSIZE; } int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5c459f2..1e556d3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1445,6 +1445,7 @@ done: if (spd.nr_pages) { int ret; + struct sock *sk = __skb->sk; /* * Drop the socket lock, otherwise we have reverse @@ -1455,9 +1456,9 @@ done: * we call into ->sendpage() with the i_mutex lock held * and networking will grab the socket lock. */ - release_sock(__skb->sk); + release_sock(sk); ret = splice_to_pipe(pipe, &spd); - lock_sock(__skb->sk); + lock_sock(sk); return ret; } diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 0ad1cd5..c77aff9 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -75,7 +75,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, end = start + skb_shinfo(skb)->frags[i].size; copy = end - offset; - if ((copy = end - offset) > 0) { + if (copy > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = frag->page; diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 6de4bd1..1e8be24 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -290,12 +290,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, while (1) { const u8 len = dccp_ackvec_len(av, index); - const u8 state = dccp_ackvec_state(av, index); + const u8 av_state = dccp_ackvec_state(av, index); /* * valid packets not yet in av_buf have a reserved * entry, with a len equal to 0. */ - if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED && + if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && len == 0 && delta == 0) { /* Found our reserved seat! */ dccp_pr_debug("Found %llu reserved seat!\n", @@ -325,31 +325,6 @@ out_duplicate: return -EILSEQ; } -#ifdef CONFIG_IP_DCCP_DEBUG -void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len) -{ - dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len, - (unsigned long long)ackno); - - while (len--) { - const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - - dccp_pr_debug_cat("%d,%d|", state, rl); - ++vector; - } - - dccp_pr_debug_cat("\n"); -} - -void dccp_ackvec_print(const struct dccp_ackvec *av) -{ - dccp_ackvector_print(av->av_buf_ackno, - av->av_buf + av->av_buf_head, - av->av_vec_len); -} -#endif - static void dccp_ackvec_throw_record(struct dccp_ackvec *av, struct dccp_ackvec_record *avr) { diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index cd61dea..a1929f3 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -159,8 +159,8 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) } else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld) - (s64)hctx->ccid3hctx_rtt >= 0) { - hctx->ccid3hctx_x = - max(min(2 * hctx->ccid3hctx_x, min_rate), + hctx->ccid3hctx_x = min(2 * hctx->ccid3hctx_x, min_rate); + hctx->ccid3hctx_x = max(hctx->ccid3hctx_x, scaled_div(((__u64)hctx->ccid3hctx_s) << 6, hctx->ccid3hctx_rtt)); hctx->ccid3hctx_t_ld = now; @@ -193,22 +193,17 @@ static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len) /* * Update Window Counter using the algorithm from [RFC 4342, 8.1]. - * The algorithm is not applicable if RTT < 4 microseconds. + * As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt(). */ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx, ktime_t now) { - u32 quarter_rtts; - - if (unlikely(hctx->ccid3hctx_rtt < 4)) /* avoid divide-by-zero */ - return; - - quarter_rtts = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count); - quarter_rtts /= hctx->ccid3hctx_rtt / 4; + u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count), + quarter_rtts = (4 * delta) / hctx->ccid3hctx_rtt; if (quarter_rtts > 0) { hctx->ccid3hctx_t_last_win_count = now; - hctx->ccid3hctx_last_win_count += min_t(u32, quarter_rtts, 5); + hctx->ccid3hctx_last_win_count += min(quarter_rtts, 5U); hctx->ccid3hctx_last_win_count &= 0xF; /* mod 16 */ } } @@ -334,8 +329,14 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) hctx->ccid3hctx_x = rfc3390_initial_rate(sk); hctx->ccid3hctx_t_ld = now; } else { - /* Sender does not have RTT sample: X_pps = 1 pkt/sec */ - hctx->ccid3hctx_x = hctx->ccid3hctx_s; + /* + * Sender does not have RTT sample: + * - set fallback RTT (RFC 4340, 3.4) since a RTT value + * is needed in several parts (e.g. window counter); + * - set sending rate X_pps = 1pps as per RFC 3448, 4.2. + */ + hctx->ccid3hctx_rtt = DCCP_FALLBACK_RTT; + hctx->ccid3hctx_x = hctx->ccid3hctx_s; hctx->ccid3hctx_x <<= 6; } ccid3_update_send_interval(hctx); diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index d1dfbb8..97ecec0 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -14,14 +14,6 @@ module_param(tfrc_debug, bool, 0444); MODULE_PARM_DESC(tfrc_debug, "Enable debug messages"); #endif -extern int tfrc_tx_packet_history_init(void); -extern void tfrc_tx_packet_history_exit(void); -extern int tfrc_rx_packet_history_init(void); -extern void tfrc_rx_packet_history_exit(void); - -extern int tfrc_li_init(void); -extern void tfrc_li_exit(void); - static int __init tfrc_module_init(void) { int rc = tfrc_li_init(); diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 1fb1187..ed98575 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -15,7 +15,7 @@ * (at your option) any later version. */ #include <linux/types.h> -#include <asm/div64.h> +#include <linux/math64.h> #include "../../dccp.h" /* internal includes that this module exports: */ #include "loss_interval.h" @@ -29,21 +29,19 @@ extern int tfrc_debug; #endif /* integer-arithmetic divisions of type (a * 1000000)/b */ -static inline u64 scaled_div(u64 a, u32 b) +static inline u64 scaled_div(u64 a, u64 b) { BUG_ON(b==0); - a *= 1000000; - do_div(a, b); - return a; + return div64_u64(a * 1000000, b); } -static inline u32 scaled_div32(u64 a, u32 b) +static inline u32 scaled_div32(u64 a, u64 b) { u64 result = scaled_div(a, b); if (result > UINT_MAX) { - DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U", - (unsigned long long)a, b); + DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX", + (unsigned long long)a, (unsigned long long)b); return UINT_MAX; } return result; @@ -58,7 +56,14 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight) return avg ? (weight * avg + (10 - weight) * newval) / 10 : newval; } -extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); -extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); +extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern int tfrc_tx_packet_history_init(void); +extern void tfrc_tx_packet_history_exit(void); +extern int tfrc_rx_packet_history_init(void); +extern void tfrc_rx_packet_history_exit(void); + +extern int tfrc_li_init(void); +extern void tfrc_li_exit(void); #endif /* _TFRC_H_ */ diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e4e64b7..2f20a29 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -661,7 +661,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) EXPORT_SYMBOL_GPL(tfrc_calc_x); -/* +/** * tfrc_calc_x_reverse_lookup - try to find p given f(p) * * @fvalue: function value to match, scaled by 1000000 @@ -676,11 +676,11 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /* Error cases. */ if (fvalue < tfrc_calc_x_lookup[0][1]) { - DCCP_WARN("fvalue %d smaller than resolution\n", fvalue); - return tfrc_calc_x_lookup[0][1]; + DCCP_WARN("fvalue %u smaller than resolution\n", fvalue); + return TFRC_SMALLEST_P; } if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) { - DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue); + DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue); return 1000000; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b348dd7..37d27bc 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -589,7 +589,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops); if (req == NULL) goto drop; @@ -605,7 +605,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; /* * Step 3: Process LISTEN state @@ -739,8 +738,8 @@ int dccp_invalid_packet(struct sk_buff *skb) * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return */ - if (dh->dccph_type >= DCCP_PKT_DATA && - dh->dccph_type <= DCCP_PKT_DATAACK && dh->dccph_x == 0) { + if ((dh->dccph_type < DCCP_PKT_DATA || + dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) { DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n", dccp_packet_name(dh->dccph_type)); return 1; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9b1129b..f7fe2a5 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -421,7 +421,6 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq6 = inet6_rsk(req); ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); - ireq6->pktopts = NULL; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 33ad483..66dca5b 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -165,12 +165,12 @@ out_free: /* See dccp_v4_conn_request */ newdmsk->dccpms_sequence_window = req->rcv_wnd; - newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - - newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss; dccp_update_gss(newsk, dreq->dreq_iss); + newdp->dccps_isr = dreq->dreq_isr; + dccp_update_gsr(newsk, dreq->dreq_isr); + /* * SWL and AWL are initially adjusted so that they are not less than * the initial Sequence Numbers received and sent, respectively: diff --git a/net/dccp/options.c b/net/dccp/options.c index d2a84a2..43bc24e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -107,9 +107,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). + * The same applies to Ack Vectors, as these depend on the CCID. * */ - if (dreq != NULL && opt >= 128) + if (dreq != NULL && (opt >= 128 || + opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { diff --git a/net/dccp/output.c b/net/dccp/output.c index 1f8a9b6..fe20068 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -508,6 +508,7 @@ void dccp_send_ack(struct sock *sk) EXPORT_SYMBOL_GPL(dccp_send_ack); +#if 0 /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */ void dccp_send_delayed_ack(struct sock *sk) { @@ -538,6 +539,7 @@ void dccp_send_delayed_ack(struct sock *sk) icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } +#endif void dccp_send_sync(struct sock *sk, const u64 ackno, const enum dccp_pkt_type pkt_type) diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 0bcdc92..81368a7 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -42,7 +42,7 @@ static int bufsize = 64 * 1024; static const char procname[] = "dccpprobe"; -struct { +static struct { struct kfifo *fifo; spinlock_t lock; wait_queue_head_t wait; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 418862f..9b539fa 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1288,7 +1288,6 @@ static void arp_format_neigh_entry(struct seq_file *seq, struct neighbour *n) { char hbuffer[HBUFFERLEN]; - const char hexbuf[] = "0123456789ABCDEF"; int k, j; char tbuf[16]; struct net_device *dev = n->dev; @@ -1302,8 +1301,8 @@ static void arp_format_neigh_entry(struct seq_file *seq, else { #endif for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < dev->addr_len; j++) { - hbuffer[k++] = hexbuf[(n->ha[j] >> 4) & 15]; - hbuffer[k++] = hexbuf[n->ha[j] & 15]; + hbuffer[k++] = hex_asc_hi(n->ha[j]); + hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } hbuffer[--k] = 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6848e47..79a7ef6 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -90,7 +90,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, - [IFA_ANYCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; @@ -536,9 +535,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]); - if (tb[IFA_ANYCAST]) - ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]); - if (tb[IFA_LABEL]) nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else @@ -745,7 +741,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; - ifa->ifa_anycast = 0; ifa->ifa_scope = 0; } @@ -1113,7 +1108,6 @@ static inline size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(4) /* IFA_ANYCAST */ + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ } @@ -1143,9 +1137,6 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, if (ifa->ifa_broadcast) NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast); - if (ifa->ifa_anycast) - NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast); - if (ifa->ifa_label[0]) NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0f1557a..0b2ac6a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -506,7 +506,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, - [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3b83c34..0d4d728 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -960,7 +960,10 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_dst_len = dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = tos; - rtm->rtm_table = tb_id; + if (tb_id < 256) + rtm->rtm_table = tb_id; + else + rtm->rtm_table = RT_TABLE_COMPAT; NLA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 828ea21..ec83448 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -419,7 +419,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, struct inet_connection_sock *icsk = inet_csk(parent); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct listen_sock *lopt = queue->listen_opt; - int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int thresh = max_retries; unsigned long now = jiffies; struct request_sock **reqp, *req; int i, budget; @@ -455,6 +456,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } } + if (queue->rskq_defer_accept) + max_retries = queue->rskq_defer_accept; + budget = 2 * (lopt->nr_table_entries / (timeout / interval)); i = lopt->clock_hand; @@ -462,8 +466,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, reqp=&lopt->syn_table[i]; while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { - if (req->retrans < thresh && - !req->rsk_ops->rtx_syn_ack(parent, req)) { + if ((req->retrans < thresh || + (inet_rsk(req)->acked && req->retrans < max_retries)) + && !req->rsk_ops->rtx_syn_ack(parent, req)) { unsigned long timeo; if (req->retrans++ == 0) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2ada033..4342cba 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -313,9 +313,8 @@ static void ipgre_tunnel_uninit(struct net_device *dev) static void ipgre_err(struct sk_buff *skb, u32 info) { -#ifndef I_WISH_WORLD_WERE_PERFECT -/* It is not :-( All the routers (except for Linux) return only +/* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. @@ -398,149 +397,6 @@ static void ipgre_err(struct sk_buff *skb, u32 info) out: read_unlock(&ipgre_lock); return; -#else - struct iphdr *iph = (struct iphdr*)dp; - struct iphdr *eiph; - __be16 *p = (__be16*)(dp+(iph->ihl<<2)); - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - int rel_type = 0; - int rel_code = 0; - __be32 rel_info = 0; - __u32 n = 0; - __be16 flags; - int grehlen = (iph->ihl<<2) + 4; - struct sk_buff *skb2; - struct flowi fl; - struct rtable *rt; - - if (p[1] != htons(ETH_P_IP)) - return; - - flags = p[0]; - if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) { - if (flags&(GRE_VERSION|GRE_ROUTING)) - return; - if (flags&GRE_CSUM) - grehlen += 4; - if (flags&GRE_KEY) - grehlen += 4; - if (flags&GRE_SEQ) - grehlen += 4; - } - if (len < grehlen + sizeof(struct iphdr)) - return; - eiph = (struct iphdr*)(dp + grehlen); - - switch (type) { - default: - return; - case ICMP_PARAMETERPROB: - n = ntohl(icmp_hdr(skb)->un.gateway) >> 24; - if (n < (iph->ihl<<2)) - return; - - /* So... This guy found something strange INSIDE encapsulated - packet. Well, he is fool, but what can we do ? - */ - rel_type = ICMP_PARAMETERPROB; - n -= grehlen; - rel_info = htonl(n << 24); - break; - - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: - /* Impossible event. */ - return; - case ICMP_FRAG_NEEDED: - /* And it is the only really necessary thing :-) */ - n = ntohs(icmp_hdr(skb)->un.frag.mtu); - if (n < grehlen+68) - return; - n -= grehlen; - /* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */ - if (n > ntohs(eiph->tot_len)) - return; - rel_info = htonl(n); - break; - default: - /* All others are translated to HOST_UNREACH. - rfc2003 contains "deep thoughts" about NET_UNREACH, - I believe, it is just ether pollution. --ANK - */ - rel_type = ICMP_DEST_UNREACH; - rel_code = ICMP_HOST_UNREACH; - break; - } - break; - case ICMP_TIME_EXCEEDED: - if (code != ICMP_EXC_TTL) - return; - break; - } - - /* Prepare fake skb to feed it to icmp_send */ - skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) - return; - dst_release(skb2->dst); - skb2->dst = NULL; - skb_pull(skb2, skb->data - (u8*)eiph); - skb_reset_network_header(skb2); - - /* Try to guess incoming interface */ - memset(&fl, 0, sizeof(fl)); - fl.fl4_dst = eiph->saddr; - fl.fl4_tos = RT_TOS(eiph->tos); - fl.proto = IPPROTO_GRE; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl)) { - kfree_skb(skb2); - return; - } - skb2->dev = rt->u.dst.dev; - - /* route "incoming" packet */ - if (rt->rt_flags&RTCF_LOCAL) { - ip_rt_put(rt); - rt = NULL; - fl.fl4_dst = eiph->daddr; - fl.fl4_src = eiph->saddr; - fl.fl4_tos = eiph->tos; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) || - rt->u.dst.dev->type != ARPHRD_IPGRE) { - ip_rt_put(rt); - kfree_skb(skb2); - return; - } - } else { - ip_rt_put(rt); - if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb2->dst->dev->type != ARPHRD_IPGRE) { - kfree_skb(skb2); - return; - } - } - - /* change mtu on this route */ - if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - if (n > dst_mtu(skb2->dst)) { - kfree_skb(skb2); - return; - } - skb2->dst->ops->update_pmtu(skb2->dst, n); - } else if (type == ICMP_TIME_EXCEEDED) { - struct ip_tunnel *t = netdev_priv(skb2->dev); - if (t->parms.iph.ttl) { - rel_type = ICMP_DEST_UNREACH; - rel_code = ICMP_HOST_UNREACH; - } - } - - icmp_send(skb2, rel_type, rel_code, rel_info); - kfree_skb(skb2); -#endif } static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 149111f..af5cb53 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -278,9 +278,8 @@ static void ipip_tunnel_uninit(struct net_device *dev) static int ipip_err(struct sk_buff *skb, u32 info) { -#ifndef I_WISH_WORLD_WERE_PERFECT -/* It is not :-( All the routers (except for Linux) return only +/* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. */ @@ -337,133 +336,6 @@ static int ipip_err(struct sk_buff *skb, u32 info) out: read_unlock(&ipip_lock); return err; -#else - struct iphdr *iph = (struct iphdr*)dp; - int hlen = iph->ihl<<2; - struct iphdr *eiph; - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - int rel_type = 0; - int rel_code = 0; - __be32 rel_info = 0; - __u32 n = 0; - struct sk_buff *skb2; - struct flowi fl; - struct rtable *rt; - - if (len < hlen + sizeof(struct iphdr)) - return 0; - eiph = (struct iphdr*)(dp + hlen); - - switch (type) { - default: - return 0; - case ICMP_PARAMETERPROB: - n = ntohl(icmp_hdr(skb)->un.gateway) >> 24; - if (n < hlen) - return 0; - - /* So... This guy found something strange INSIDE encapsulated - packet. Well, he is fool, but what can we do ? - */ - rel_type = ICMP_PARAMETERPROB; - rel_info = htonl((n - hlen) << 24); - break; - - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: - /* Impossible event. */ - return 0; - case ICMP_FRAG_NEEDED: - /* And it is the only really necessary thing :-) */ - n = ntohs(icmp_hdr(skb)->un.frag.mtu); - if (n < hlen+68) - return 0; - n -= hlen; - /* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */ - if (n > ntohs(eiph->tot_len)) - return 0; - rel_info = htonl(n); - break; - default: - /* All others are translated to HOST_UNREACH. - rfc2003 contains "deep thoughts" about NET_UNREACH, - I believe, it is just ether pollution. --ANK - */ - rel_type = ICMP_DEST_UNREACH; - rel_code = ICMP_HOST_UNREACH; - break; - } - break; - case ICMP_TIME_EXCEEDED: - if (code != ICMP_EXC_TTL) - return 0; - break; - } - - /* Prepare fake skb to feed it to icmp_send */ - skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) - return 0; - dst_release(skb2->dst); - skb2->dst = NULL; - skb_pull(skb2, skb->data - (u8*)eiph); - skb_reset_network_header(skb2); - - /* Try to guess incoming interface */ - memset(&fl, 0, sizeof(fl)); - fl.fl4_daddr = eiph->saddr; - fl.fl4_tos = RT_TOS(eiph->tos); - fl.proto = IPPROTO_IPIP; - if (ip_route_output_key(dev_net(skb->dev), &rt, &key)) { - kfree_skb(skb2); - return 0; - } - skb2->dev = rt->u.dst.dev; - - /* route "incoming" packet */ - if (rt->rt_flags&RTCF_LOCAL) { - ip_rt_put(rt); - rt = NULL; - fl.fl4_daddr = eiph->daddr; - fl.fl4_src = eiph->saddr; - fl.fl4_tos = eiph->tos; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) || - rt->u.dst.dev->type != ARPHRD_TUNNEL) { - ip_rt_put(rt); - kfree_skb(skb2); - return 0; - } - } else { - ip_rt_put(rt); - if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb2->dst->dev->type != ARPHRD_TUNNEL) { - kfree_skb(skb2); - return 0; - } - } - - /* change mtu on this route */ - if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - if (n > dst_mtu(skb2->dst)) { - kfree_skb(skb2); - return 0; - } - skb2->dst->ops->update_pmtu(skb2->dst, n); - } else if (type == ICMP_TIME_EXCEEDED) { - struct ip_tunnel *t = netdev_priv(skb2->dev); - if (t->parms.iph.ttl) { - rel_type = ICMP_DEST_UNREACH; - rel_code = ICMP_HOST_UNREACH; - } - } - - icmp_send(skb2, rel_type, rel_code, rel_info); - kfree_skb(skb2); - return 0; -#endif } static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph, diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 0457859..d2a887f 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -556,7 +556,6 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) spin_lock_bh(&nf_nat_lock); hlist_del_rcu(&nat->bysource); - nat->ct = NULL; spin_unlock_bh(&nf_nat_lock); } @@ -570,8 +569,8 @@ static void nf_nat_move_storage(void *new, void *old) return; spin_lock_bh(&nf_nat_lock); - hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); new_nat->ct = ct; + hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); spin_unlock_bh(&nf_nat_lock); } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 5daefad..7750c97 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -232,6 +232,11 @@ static unsigned char asn1_length_decode(struct asn1_ctx *ctx, } } } + + /* don't trust len bigger than ctx buffer */ + if (*len > ctx->end - ctx->pointer) + return 0; + return 1; } @@ -250,6 +255,10 @@ static unsigned char asn1_header_decode(struct asn1_ctx *ctx, if (!asn1_length_decode(ctx, &def, &len)) return 0; + /* primitive shall be definite, indefinite shall be constructed */ + if (*con == ASN1_PRI && !def) + return 0; + if (def) *eoc = ctx->pointer + len; else @@ -434,6 +443,11 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx, unsigned long *optr; size = eoc - ctx->pointer + 1; + + /* first subid actually encodes first two subids */ + if (size < 2 || size > ULONG_MAX/sizeof(unsigned long)) + return 0; + *oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC); if (*oid == NULL) { if (net_ratelimit()) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index fead049..37a1ecd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -608,6 +608,14 @@ static void raw_close(struct sock *sk, long timeout) sk_common_release(sk); } +static int raw_destroy(struct sock *sk) +{ + lock_sock(sk); + ip_flush_pending_frames(sk); + release_sock(sk); + return 0; +} + /* This gets rid of all the nasties in af_inet. -DaveM */ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -820,6 +828,7 @@ struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, .close = raw_close, + .destroy = raw_destroy, .connect = ip4_datagram_connect, .disconnect = udp_disconnect, .ioctl = raw_ioctl, @@ -925,7 +934,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) srcp = inet->num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", i, src, srcp, dest, destp, sp->sk_state, atomic_read(&sp->sk_wmem_alloc), atomic_read(&sp->sk_rmem_alloc), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 92f90ae..96be336 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -160,7 +160,7 @@ static struct dst_ops ipv4_dst_ops = { .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, - .local_out = ip_local_out, + .local_out = __ip_local_out, .entry_size = sizeof(struct rtable), .entries = ATOMIC_INIT(0), }; @@ -1792,7 +1792,7 @@ static int __mkroute_input(struct sk_buff *skb, if (err) flags |= RTCF_DIRECTSRC; - if (out_dev == in_dev && err && !(flags & RTCF_MASQ) && + if (out_dev == in_dev && err && (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) flags |= RTCF_DOREDIRECT; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 73ba989..d182a2a 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -285,7 +285,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, cookie_check_timestamp(&tcp_opt); ret = NULL; - req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) goto out; @@ -301,7 +301,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->rmt_port = th->source; ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->rcv_wscale = tcp_opt.rcv_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f886531..fc54a48 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1227,7 +1227,14 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, copied += used; offset += used; } - if (offset != skb->len) + /* + * If recv_actor drops the lock (e.g. TCP splice + * receive) the skb pointer might be invalid when + * getting here: tcp_collapse might have deleted it + * while aggregating skbs from the socket queue. + */ + skb = tcp_recv_skb(sk, seq-1, &offset); + if (!skb || (offset+1 != skb->len)) break; } if (tcp_hdr(skb)->fin) { @@ -2105,12 +2112,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_DEFER_ACCEPT: - if (val < 0) { - err = -EINVAL; - } else { - if (val > MAX_TCP_ACCEPT_DEFERRED) - val = MAX_TCP_ACCEPT_DEFERRED; - icsk->icsk_accept_queue.rskq_defer_accept = val; + icsk->icsk_accept_queue.rskq_defer_accept = 0; + if (val > 0) { + /* Translate value in seconds to number of + * retransmits */ + while (icsk->icsk_accept_queue.rskq_defer_accept < 32 && + val > ((TCP_TIMEOUT_INIT / HZ) << + icsk->icsk_accept_queue.rskq_defer_accept)) + icsk->icsk_accept_queue.rskq_defer_accept++; + icsk->icsk_accept_queue.rskq_defer_accept++; } break; @@ -2292,7 +2302,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: - val = icsk->icsk_accept_queue.rskq_defer_accept; + val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 : + ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1)); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b54d9d3..cad73b7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1392,9 +1392,9 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, if (before(next_dup->start_seq, skip_to_seq)) { skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count); - tcp_sacktag_walk(skb, sk, NULL, - next_dup->start_seq, next_dup->end_seq, - 1, fack_count, reord, flag); + skb = tcp_sacktag_walk(skb, sk, NULL, + next_dup->start_seq, next_dup->end_seq, + 1, fack_count, reord, flag); } return skb; @@ -2483,6 +2483,20 @@ static inline void tcp_complete_cwr(struct sock *sk) tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } +static void tcp_try_keep_open(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int state = TCP_CA_Open; + + if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) + state = TCP_CA_Disorder; + + if (inet_csk(sk)->icsk_ca_state != state) { + tcp_set_ca_state(sk, state); + tp->high_seq = tp->snd_nxt; + } +} + static void tcp_try_to_open(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -2496,15 +2510,7 @@ static void tcp_try_to_open(struct sock *sk, int flag) tcp_enter_cwr(sk, 1); if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { - int state = TCP_CA_Open; - - if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) - state = TCP_CA_Disorder; - - if (inet_csk(sk)->icsk_ca_state != state) { - tcp_set_ca_state(sk, state); - tp->high_seq = tp->snd_nxt; - } + tcp_try_keep_open(sk); tcp_moderate_cwnd(tp); } else { tcp_cwnd_down(sk, flag); @@ -3310,8 +3316,11 @@ no_queue: return 1; old_ack: - if (TCP_SKB_CB(skb)->sacked) + if (TCP_SKB_CB(skb)->sacked) { tcp_sacktag_write_queue(sk, skb, prior_snd_una); + if (icsk->icsk_ca_state == TCP_CA_Open) + tcp_try_keep_open(sk); + } uninteresting_ack: SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt); @@ -4532,49 +4541,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th) } } -static int tcp_defer_accept_check(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->defer_tcp_accept.request) { - int queued_data = tp->rcv_nxt - tp->copied_seq; - int hasfin = !skb_queue_empty(&sk->sk_receive_queue) ? - tcp_hdr((struct sk_buff *) - sk->sk_receive_queue.prev)->fin : 0; - - if (queued_data && hasfin) - queued_data--; - - if (queued_data && - tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) { - if (sock_flag(sk, SOCK_KEEPOPEN)) { - inet_csk_reset_keepalive_timer(sk, - keepalive_time_when(tp)); - } else { - inet_csk_delete_keepalive_timer(sk); - } - - inet_csk_reqsk_queue_add( - tp->defer_tcp_accept.listen_sk, - tp->defer_tcp_accept.request, - sk); - - tp->defer_tcp_accept.listen_sk->sk_data_ready( - tp->defer_tcp_accept.listen_sk, 0); - - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } else if (hasfin || - tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) { - tcp_reset(sk); - return -1; - } - } - return 0; -} - static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); @@ -4935,8 +4901,6 @@ step5: tcp_data_snd_check(sk); tcp_ack_snd_check(sk); - - tcp_defer_accept_check(sk); return 0; csum_error: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cd601a8..12695be 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -85,10 +85,6 @@ int sysctl_tcp_tw_reuse __read_mostly; int sysctl_tcp_low_latency __read_mostly; -/* Check TCP sequence numbers in ICMP packets. */ -#define ICMP_MIN_LENGTH 8 - -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, @@ -1285,7 +1281,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&tcp_request_sock_ops); + req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) goto drop; @@ -1918,14 +1914,6 @@ int tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } - if (tp->defer_tcp_accept.request) { - reqsk_free(tp->defer_tcp_accept.request); - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } - atomic_dec(&tcp_sockets_allocated); return 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 019c8c1..8245247 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -571,8 +571,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, does sequence test, SYN is truncated, and thus we consider it a bare ACK. - Both ends (listening sockets) accept the new incoming - connection and try to talk to each other. 8-) + If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this + bare ACK. Otherwise, we create an established connection. Both + ends (listening sockets) accept the new incoming connection and try + to talk to each other. 8-) Note: This case is both harmless, and rare. Possibility is about the same as us discovering intelligent life on another plant tomorrow. @@ -640,6 +642,13 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; + /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ + if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; + return NULL; + } + /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all * the tests. THIS SEGMENT MUST MOVE SOCKET TO @@ -678,24 +687,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, inet_csk_reqsk_queue_unlink(sk, req, prev); inet_csk_reqsk_queue_removed(sk, req); - if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && - TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { - - /* the accept queue handling is done is est recv slow - * path so lets make sure to start there - */ - tcp_sk(child)->pred_flags = 0; - sock_hold(sk); - sock_hold(child); - tcp_sk(child)->defer_tcp_accept.listen_sk = sk; - tcp_sk(child)->defer_tcp_accept.request = req; - - inet_csk_reset_keepalive_timer(child, - inet_csk(sk)->icsk_accept_queue.rskq_defer_accept * HZ); - } else { - inet_csk_reqsk_queue_add(sk, req, child); - } - + inet_csk_reqsk_queue_add(sk, req, child); return child; listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index debf235..ad993ec 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1836,7 +1836,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - unsigned int cur_mss = tcp_current_mss(sk, 0); + unsigned int cur_mss; int err; /* Inconslusive MTU probe */ @@ -1858,6 +1858,11 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) return -ENOMEM; } + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) + return -EHOSTUNREACH; /* Routing failure or similar. */ + + cur_mss = tcp_current_mss(sk, 0); + /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case @@ -1884,9 +1889,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) (sysctl_tcp_retrans_collapse != 0)) tcp_retrans_try_collapse(sk, skb, cur_mss); - if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) - return -EHOSTUNREACH; /* Routing failure or similar. */ - /* Some Solaris stacks overoptimize and ignore the FIN on a * retransmit when old data is attached. So strip it off * since it is cheap to do so and saves bytes on the network. @@ -2129,6 +2131,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) TCP_SKB_CB(skb)->when = tcp_time_stamp; if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(LINUX_MIB_TCPABORTFAILED); + + TCP_INC_STATS(TCP_MIB_OUTRSTS); } /* WARNING: This routine must only be called when we have already sent diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4de68cf..63ed9d6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -489,11 +489,6 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { - tcp_send_active_reset(sk, GFP_ATOMIC); - goto death; - } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) goto out; diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index d3b709a..cb1f0e8 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -97,7 +97,7 @@ static int tunnel64_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for (handler = tunnel64_handlers; handler; handler = handler->next) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db1cb7c..56fcda3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -420,7 +420,7 @@ void udp_err(struct sk_buff *skb, u32 info) /* * Throw away all pending data and cancel the corking. Socket is locked. */ -static void udp_flush_pending_frames(struct sock *sk) +void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -430,6 +430,7 @@ static void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } +EXPORT_SYMBOL(udp_flush_pending_frames); /** * udp4_hwcsum_outgoing - handle outgoing HW checksumming diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 584e6d7..7135279 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -52,7 +52,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) IP_ECN_clear(top_iph); top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? - 0 : XFRM_MODE_SKB_CB(skb)->frag_off; + 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); ip_select_ident(top_iph, dst->child, NULL); top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e591e09..147588f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -731,8 +731,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) onlink = -1; spin_lock(&ifa->lock); - lifetime = min_t(unsigned long, - ifa->valid_lft, 0x7fffffffUL/HZ); + + lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); + /* + * Note: Because this address is + * not permanent, lifetime < + * LONG_MAX / HZ here. + */ if (time_before(expires, ifa->tstamp + lifetime * HZ)) expires = ifa->tstamp + lifetime * HZ; @@ -1722,7 +1727,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) __u32 valid_lft; __u32 prefered_lft; int addr_type; - unsigned long rt_expires; struct inet6_dev *in6_dev; pinfo = (struct prefix_info *) opt; @@ -1764,41 +1768,49 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) * 2) Configure prefixes with the auto flag set */ - /* Avoid arithmetic overflow. Really, we could - save rt_expires in seconds, likely valid_lft, - but it would require division in fib gc, that it - not good. - */ - if (valid_lft >= 0x7FFFFFFF/HZ) - rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ); - else - rt_expires = valid_lft * HZ; - - /* - * We convert this (in jiffies) to clock_t later. - * Avoid arithmetic overflow there as well. - * Overflow can happen only if HZ < USER_HZ. - */ - if (HZ < USER_HZ && rt_expires > 0x7FFFFFFF / USER_HZ) - rt_expires = 0x7FFFFFFF / USER_HZ; - if (pinfo->onlink) { struct rt6_info *rt; + unsigned long rt_expires; + + /* Avoid arithmetic overflow. Really, we could + * save rt_expires in seconds, likely valid_lft, + * but it would require division in fib gc, that it + * not good. + */ + if (HZ > USER_HZ) + rt_expires = addrconf_timeout_fixup(valid_lft, HZ); + else + rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); + + if (addrconf_finite_timeout(rt_expires)) + rt_expires *= HZ; + rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, dev->ifindex, 1); if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { - if (rt->rt6i_flags&RTF_EXPIRES) { - if (valid_lft == 0) { - ip6_del_rt(rt); - rt = NULL; - } else { - rt->rt6i_expires = jiffies + rt_expires; - } + /* Autoconf prefix route */ + if (valid_lft == 0) { + ip6_del_rt(rt); + rt = NULL; + } else if (addrconf_finite_timeout(rt_expires)) { + /* not infinity */ + rt->rt6i_expires = jiffies + rt_expires; + rt->rt6i_flags |= RTF_EXPIRES; + } else { + rt->rt6i_flags &= ~RTF_EXPIRES; + rt->rt6i_expires = 0; } } else if (valid_lft) { + clock_t expires = 0; + int flags = RTF_ADDRCONF | RTF_PREFIX_RT; + if (addrconf_finite_timeout(rt_expires)) { + /* not infinity */ + flags |= RTF_EXPIRES; + expires = jiffies_to_clock_t(rt_expires); + } addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, - dev, jiffies_to_clock_t(rt_expires), RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT); + dev, expires, flags); } if (rt) dst_release(&rt->u.dst); @@ -2014,17 +2026,22 @@ err_exit: * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, - int plen, __u8 ifa_flags, __u32 prefered_lft, + unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; int scope; - u32 flags = RTF_EXPIRES; + u32 flags; + clock_t expires; + unsigned long timeout; ASSERT_RTNL(); + if (plen > 128) + return -EINVAL; + /* check the lifetime */ if (!valid_lft || prefered_lft > valid_lft) return -EINVAL; @@ -2038,17 +2055,23 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, scope = ipv6_addr_scope(pfx); - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; + flags = RTF_EXPIRES; + } else { + expires = 0; flags = 0; - } else if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + ifa_flags |= IFA_F_PERMANENT; + } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); @@ -2060,7 +2083,7 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, spin_unlock_bh(&ifp->lock); addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, - jiffies_to_clock_t(valid_lft * HZ), flags); + expires, flags); /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for @@ -2076,12 +2099,15 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, } static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, - int plen) + unsigned int plen) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; + if (plen > 128) + return -EINVAL; + dev = __dev_get_by_index(net, ifindex); if (!dev) return -ENODEV; @@ -3148,22 +3174,30 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, u32 prefered_lft, u32 valid_lft) { - u32 flags = RTF_EXPIRES; + u32 flags; + clock_t expires; + unsigned long timeout; if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; + flags = RTF_EXPIRES; + } else { + expires = 0; flags = 0; - } else if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + ifa_flags |= IFA_F_PERMANENT; + } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } spin_lock_bh(&ifp->lock); ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; @@ -3176,7 +3210,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, ipv6_ifa_notify(0, ifp); addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, - jiffies_to_clock_t(valid_lft * HZ), flags); + expires, flags); addrconf_verify(0); return 0; @@ -4242,7 +4276,7 @@ static void addrconf_sysctl_register(struct inet6_dev *idev) neigh_sysctl_register(idev->dev, idev->nd_parms, NET_IPV6, NET_IPV6_NEIGH, "ipv6", &ndisc_ifinfo_sysctl_change, - NULL); + ndisc_ifinfo_sysctl_strategy); __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, idev, &idev->cnf); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3c6aafb..e84b3fd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -191,7 +191,7 @@ lookup_protocol: np->mcast_hops = -1; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->ipv6only = init_net.ipv6.sysctl.bindv6only; + np->ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 94fa6ae..0f0f94a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -496,7 +496,8 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) return 0; } -int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, +int datagram_send_ctl(struct net *net, + struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, int *hlimit, int *tclass) { @@ -509,7 +510,6 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { int addr_type; - struct net_device *dev = NULL; if (!CMSG_OK(msg, cmsg)) { err = -EINVAL; @@ -522,6 +522,9 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, switch (cmsg->cmsg_type) { case IPV6_PKTINFO: case IPV6_2292PKTINFO: + { + struct net_device *dev = NULL; + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; goto exit_f; @@ -535,32 +538,32 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, fl->oif = src_info->ipi6_ifindex; } - addr_type = ipv6_addr_type(&src_info->ipi6_addr); + addr_type = __ipv6_addr_type(&src_info->ipi6_addr); - if (addr_type == IPV6_ADDR_ANY) - break; + if (fl->oif) { + dev = dev_get_by_index(net, fl->oif); + if (!dev) + return -ENODEV; + } else if (addr_type & IPV6_ADDR_LINKLOCAL) + return -EINVAL; - if (addr_type & IPV6_ADDR_LINKLOCAL) { - if (!src_info->ipi6_ifindex) - return -EINVAL; - else { - dev = dev_get_by_index(&init_net, src_info->ipi6_ifindex); - if (!dev) - return -ENODEV; - } - } - if (!ipv6_chk_addr(&init_net, &src_info->ipi6_addr, - dev, 0)) { - if (dev) - dev_put(dev); - err = -EINVAL; - goto exit_f; + if (addr_type != IPV6_ADDR_ANY) { + int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; + if (!ipv6_chk_addr(net, &src_info->ipi6_addr, + strict ? dev : NULL, 0)) + err = -EINVAL; + else + ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); } + if (dev) dev_put(dev); - ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); + if (err) + goto exit_f; + break; + } case IPV6_FLOWINFO: if (cmsg->cmsg_len < CMSG_LEN(4)) { @@ -702,6 +705,11 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, } *hlimit = *(int *)CMSG_DATA(cmsg); + if (*hlimit < -1 || *hlimit > 0xff) { + err = -EINVAL; + goto exit_f; + } + break; case IPV6_TCLASS: diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index eb7a940..37a4e77 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -354,7 +354,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_control = (void*)(fl->opt+1); flowi.oif = 0; - err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk); + err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 4e5c861..17eb48b 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -102,6 +102,15 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (hdr->version != 6) goto err; + /* + * RFC4291 2.5.3 + * A packet received on an interface with a destination address + * of loopback must be dropped. + */ + if (!(dev->flags & IFF_LOOPBACK) && + ipv6_addr_loopback(&hdr->daddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 2de3c46..1479618 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -197,7 +197,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) const char *name = vif->dev ? vif->dev->name : "none"; seq_printf(seq, - "%2Zd %-10s %8ld %7ld %8ld %7ld %05X\n", + "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", vif - vif6_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 56d55fe..86e28a7 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -67,7 +67,7 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW) - return -EINVAL; + return -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -161,9 +161,17 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct ipv6_txoptions *opt; struct sk_buff *pktopt; - if (sk->sk_protocol != IPPROTO_UDP && - sk->sk_protocol != IPPROTO_UDPLITE && - sk->sk_protocol != IPPROTO_TCP) + if (sk->sk_type == SOCK_RAW) + break; + + if (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_UDPLITE) { + struct udp_sock *up = udp_sk(sk); + if (up->pending == AF_INET6) { + retv = -EBUSY; + break; + } + } else if (sk->sk_protocol != IPPROTO_TCP) break; if (sk->sk_state != TCP_ESTABLISHED) { @@ -337,18 +345,21 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + + /* remove any sticky options header with a zero option + * length, per RFC3542. + */ if (optlen == 0) optval = NULL; + else if (optlen < sizeof(struct ipv6_opt_hdr) || + optlen & 0x7 || optlen > 8 * 255) + goto e_inval; /* hop-by-hop / destination options are privileged option */ retv = -EPERM; if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) break; - if (optlen < sizeof(struct ipv6_opt_hdr) || - optlen & 0x7 || optlen > 8 * 255) - goto e_inval; - opt = ipv6_renew_options(sk, np->opt, optname, (struct ipv6_opt_hdr __user *)optval, optlen); @@ -416,7 +427,7 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk); + retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk); if (retv) goto done; update: @@ -438,7 +449,7 @@ done: case IPV6_MULTICAST_HOPS: if (sk->sk_type == SOCK_STREAM) - goto e_inval; + break; if (optlen < sizeof(int)) goto e_inval; if (val > 255 || val < -1) @@ -450,13 +461,15 @@ done: case IPV6_MULTICAST_LOOP: if (optlen < sizeof(int)) goto e_inval; + if (val != valbool) + goto e_inval; np->mc_loop = valbool; retv = 0; break; case IPV6_MULTICAST_IF: if (sk->sk_type == SOCK_STREAM) - goto e_inval; + break; if (optlen < sizeof(int)) goto e_inval; @@ -832,7 +845,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, len = min_t(unsigned int, len, ipv6_optlen(hdr)); if (copy_to_user(optval, hdr, len)) return -EFAULT; - return ipv6_optlen(hdr); + return len; } static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, @@ -852,7 +865,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) - return -EINVAL; + return -ENOPROTOOPT; if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; val = sk->sk_family; @@ -866,6 +879,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, return -EINVAL; if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) return -EFAULT; + if (gsf.gf_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; lock_sock(sk); err = ip6_mc_msfget(sk, &gsf, (struct group_filter __user *)optval, optlen); @@ -975,6 +990,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, len = ipv6_getsockopt_sticky(sk, np->opt, optname, optval, len); release_sock(sk); + /* check if ipv6_getsockopt_sticky() returns err code */ + if (len < 0) + return len; return put_user(len, optlen); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a55fc05..282fdb3 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1727,10 +1727,10 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * f return ret; } -static int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, int __user *name, - int nlen, void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen) +int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, int __user *name, + int nlen, void __user *oldval, + size_t __user *oldlenp, + void __user *newval, size_t newlen) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2dccad4..e65e26e 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -209,7 +209,9 @@ fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) arg.dst = dst; hash = ip6qhashfn(id, src, dst); + local_bh_disable(); q = inet_frag_find(&nf_init_frags, &nf_frags, &arg, hash); + local_bh_enable(); if (q == NULL) goto oom; @@ -638,10 +640,10 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) goto ret_orig; } - spin_lock(&fq->q.lock); + spin_lock_bh(&fq->q.lock); if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) { - spin_unlock(&fq->q.lock); + spin_unlock_bh(&fq->q.lock); pr_debug("Can't insert skb to queue\n"); fq_put(fq); goto ret_orig; @@ -653,7 +655,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) if (ret_skb == NULL) pr_debug("Can't reassemble fragmented packets\n"); } - spin_unlock(&fq->q.lock); + spin_unlock_bh(&fq->q.lock); fq_put(fq); return ret_skb; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 232e0dc..3aee123 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -813,7 +813,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1164,6 +1164,15 @@ static void rawv6_close(struct sock *sk, long timeout) sk_common_release(sk); } +static int raw6_destroy(struct sock *sk) +{ + lock_sock(sk); + ip6_flush_pending_frames(sk); + release_sock(sk); + + return inet6_destroy_sock(sk); +} + static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); @@ -1187,11 +1196,11 @@ struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, + .destroy = raw6_destroy, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, - .destroy = inet6_destroy_sock, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 12bba08..d1f3e19 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -109,7 +109,7 @@ static struct dst_ops ip6_dst_ops_template = { .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, - .local_out = ip6_local_out, + .local_out = __ip6_local_out, .entry_size = sizeof(struct rt6_info), .entries = ATOMIC_INIT(0), }; @@ -446,7 +446,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; unsigned int pref; - u32 lifetime; + unsigned long lifetime; struct rt6_info *rt; if (len < sizeof(struct route_info)) { @@ -472,13 +472,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (pref == ICMPV6_ROUTER_PREF_INVALID) pref = ICMPV6_ROUTER_PREF_MEDIUM; - lifetime = ntohl(rinfo->lifetime); - if (lifetime == 0xffffffff) { - /* infinity */ - } else if (lifetime > 0x7fffffff/HZ) { - /* Avoid arithmetic overflow */ - lifetime = 0x7fffffff/HZ - 1; - } + lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; @@ -506,7 +500,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (lifetime == 0xffffffff) { + if (!addrconf_finite_timeout(lifetime)) { rt->rt6i_flags &= ~RTF_EXPIRES; } else { rt->rt6i_expires = jiffies + HZ * lifetime; @@ -1106,7 +1100,9 @@ int ip6_route_add(struct fib6_config *cfg) } rt->u.dst.obsolete = -1; - rt->rt6i_expires = jiffies + clock_t_to_jiffies(cfg->fc_expires); + rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ? + jiffies + clock_t_to_jiffies(cfg->fc_expires) : + 0; if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; @@ -2200,7 +2196,13 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); - expires = rt->rt6i_expires ? rt->rt6i_expires - jiffies : 0; + if (!(rt->rt6i_flags & RTF_EXPIRES)) + expires = 0; + else if (rt->rt6i_expires - jiffies < INT_MAX) + expires = rt->rt6i_expires - jiffies; + else + expires = INT_MAX; + if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, expires, rt->u.dst.error) < 0) goto nla_put_failure; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5a6fab9..32e871a 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -222,15 +222,18 @@ __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) } -static int ipip6_tunnel_get_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) +static int ipip6_tunnel_get_prl(struct ip_tunnel *t, + struct ip_tunnel_prl __user *a) { - struct ip_tunnel_prl *kp; + struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; unsigned int cmax, c = 0, ca, len; int ret = 0; - cmax = a->datalen / sizeof(*a); - if (cmax > 1 && a->addr != htonl(INADDR_ANY)) + if (copy_from_user(&kprl, a, sizeof(kprl))) + return -EFAULT; + cmax = kprl.datalen / sizeof(kprl); + if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) cmax = 1; /* For simple GET or for root users, @@ -261,26 +264,25 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) for (prl = t->prl; prl; prl = prl->next) { if (c > cmax) break; - if (a->addr != htonl(INADDR_ANY) && prl->addr != a->addr) + if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; c++; - if (a->addr != htonl(INADDR_ANY)) + if (kprl.addr != htonl(INADDR_ANY)) break; } out: read_unlock(&ipip6_lock); len = sizeof(*kp) * c; - ret = len ? copy_to_user(a->data, kp, len) : 0; + ret = 0; + if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) + ret = -EFAULT; kfree(kp); - if (ret) - return -EFAULT; - a->datalen = len; - return 0; + return ret; } static int @@ -403,9 +405,8 @@ static void ipip6_tunnel_uninit(struct net_device *dev) static int ipip6_err(struct sk_buff *skb, u32 info) { -#ifndef I_WISH_WORLD_WERE_PERFECT -/* It is not :-( All the routers (except for Linux) return only +/* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. */ @@ -462,92 +463,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) out: read_unlock(&ipip6_lock); return err; -#else - struct iphdr *iph = (struct iphdr*)dp; - int hlen = iph->ihl<<2; - struct ipv6hdr *iph6; - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - int rel_type = 0; - int rel_code = 0; - int rel_info = 0; - struct sk_buff *skb2; - struct rt6_info *rt6i; - - if (len < hlen + sizeof(struct ipv6hdr)) - return; - iph6 = (struct ipv6hdr*)(dp + hlen); - - switch (type) { - default: - return; - case ICMP_PARAMETERPROB: - if (icmp_hdr(skb)->un.gateway < hlen) - return; - - /* So... This guy found something strange INSIDE encapsulated - packet. Well, he is fool, but what can we do ? - */ - rel_type = ICMPV6_PARAMPROB; - rel_info = icmp_hdr(skb)->un.gateway - hlen; - break; - - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: - /* Impossible event. */ - return; - case ICMP_FRAG_NEEDED: - /* Too complicated case ... */ - return; - default: - /* All others are translated to HOST_UNREACH. - rfc2003 contains "deep thoughts" about NET_UNREACH, - I believe, it is just ether pollution. --ANK - */ - rel_type = ICMPV6_DEST_UNREACH; - rel_code = ICMPV6_ADDR_UNREACH; - break; - } - break; - case ICMP_TIME_EXCEEDED: - if (code != ICMP_EXC_TTL) - return; - rel_type = ICMPV6_TIME_EXCEED; - rel_code = ICMPV6_EXC_HOPLIMIT; - break; - } - - /* Prepare fake skb to feed it to icmpv6_send */ - skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) - return 0; - dst_release(skb2->dst); - skb2->dst = NULL; - skb_pull(skb2, skb->data - (u8*)iph6); - skb_reset_network_header(skb2); - - /* Try to guess incoming interface */ - rt6i = rt6_lookup(dev_net(skb->dev), &iph6->saddr, NULL, NULL, 0); - if (rt6i && rt6i->rt6i_dev) { - skb2->dev = rt6i->rt6i_dev; - - rt6i = rt6_lookup(dev_net(skb->dev), - &iph6->daddr, &iph6->saddr, NULL, 0); - - if (rt6i && rt6i->rt6i_dev && rt6i->rt6i_dev->type == ARPHRD_SIT) { - struct ip_tunnel *t = netdev_priv(rt6i->rt6i_dev); - if (rel_type == ICMPV6_TIME_EXCEED && t->parms.iph.ttl) { - rel_type = ICMPV6_DEST_UNREACH; - rel_code = ICMPV6_ADDR_UNREACH; - } - icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev); - } - } - kfree_skb(skb2); - return 0; -#endif } static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) @@ -960,11 +875,20 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; case SIOCGETPRL: + err = -EINVAL; + if (dev == sitn->fb_tunnel_dev) + goto done; + err = -ENOENT; + if (!(t = netdev_priv(dev))) + goto done; + err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data); + break; + case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: err = -EPERM; - if (cmd != SIOCGETPRL && !capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) goto done; err = -EINVAL; if (dev == sitn->fb_tunnel_dev) @@ -977,12 +901,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; switch (cmd) { - case SIOCGETPRL: - err = ipip6_tunnel_get_prl(t, &prl); - if (!err && copy_to_user(ifr->ifr_ifru.ifru_data, - &prl, sizeof(prl))) - err = -EFAULT; - break; case SIOCDELPRL: err = ipip6_tunnel_del_prl(t, &prl); break; @@ -991,8 +909,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } - if (cmd != SIOCGETPRL) - netdev_state_change(dev); + netdev_state_change(dev); break; default: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 938ce4e..3ecc115 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -198,7 +198,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq6 = inet6_rsk(req); treq = tcp_rsk(req); - ireq6->pktopts = NULL; if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 715965f..cb46749 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1299,7 +1299,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq = inet6_rsk(req); ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); - treq->pktopts = NULL; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 6323921..669f280 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -109,7 +109,7 @@ static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; for (handler = tunnel46_handlers; handler; handler = handler->next) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1fd784f..dd30962 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -534,7 +534,9 @@ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); - if (up->pending) { + if (up->pending == AF_INET) + udp_flush_pending_frames(sk); + else if (up->pending) { up->len = 0; up->pending = 0; ip6_flush_pending_frames(sk); @@ -731,7 +733,7 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -848,12 +850,14 @@ do_append_data: } else { dst_release(dst); } + dst = NULL; } if (err > 0) err = np->recverr ? net_xmit_errno(err) : 0; release_sock(sk); out: + dst_release(dst); fl6_sock_release(flowlabel); if (!err) return len; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index ae54b20..3eb5bcc 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1093,11 +1093,6 @@ static int irda_create(struct net *net, struct socket *sock, int protocol) init_waitqueue_head(&self->query_wait); - /* Initialise networking socket struct */ - sock_init_data(sock, sk); /* Note : set sk->sk_refcnt to 1 */ - sk->sk_family = PF_IRDA; - sk->sk_protocol = protocol; - switch (sock->type) { case SOCK_STREAM: sock->ops = &irda_stream_ops; @@ -1124,13 +1119,20 @@ static int irda_create(struct net *net, struct socket *sock, int protocol) self->max_sdu_size_rx = TTP_SAR_UNBOUND; break; default: + sk_free(sk); return -ESOCKTNOSUPPORT; } break; default: + sk_free(sk); return -ESOCKTNOSUPPORT; } + /* Initialise networking socket struct */ + sock_init_data(sock, sk); /* Note : set sk->sk_refcnt to 1 */ + sk->sk_family = PF_IRDA; + sk->sk_protocol = protocol; + /* Register as a client with IrLMP */ self->ckey = irlmp_register_client(0, NULL, NULL, NULL); self->mask.word = 0xffff; diff --git a/net/key/af_key.c b/net/key/af_key.c index 9e7236f..7470e36 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1251,7 +1251,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr, x->sel.prefixlen_s = addr->sadb_address_prefixlen; } - if (x->props.mode == XFRM_MODE_TRANSPORT) + if (!x->sel.family) x->sel.family = x->props.family; if (ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]) { @@ -3030,6 +3030,9 @@ static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c) static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) { + if (atomic_read(&pfkey_socks_nr) == 0) + return 0; + switch (c->event) { case XFRM_MSG_EXPIRE: return key_notify_sa_expire(x, c); diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index e2ddde7..008de1f 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -286,12 +286,14 @@ void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb, * * Sends received pdus to the sap state machine. */ -static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb) +static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, + struct sock *sk) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->type = LLC_SAP_EV_TYPE_PDU; ev->reason = 0; + skb->sk = sk; llc_sap_state_process(sap, skb); } @@ -360,8 +362,7 @@ static void llc_sap_mcast(struct llc_sap *sap, break; sock_hold(sk); - skb_set_owner_r(skb1, sk); - llc_sap_rcv(sap, skb1); + llc_sap_rcv(sap, skb1, sk); sock_put(sk); } read_unlock_bh(&sap->sk_list.lock); @@ -381,8 +382,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) } else { struct sock *sk = llc_lookup_dgram(sap, &laddr); if (sk) { - skb_set_owner_r(skb, sk); - llc_sap_rcv(sap, skb); + llc_sap_rcv(sap, skb, sk); sock_put(sk); } else kfree_skb(skb); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 699d97b..a9fce4a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -672,7 +672,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (params->vlan) { sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); - if (sdata->vif.type != IEEE80211_IF_TYPE_VLAN || + if (sdata->vif.type != IEEE80211_IF_TYPE_VLAN && sdata->vif.type != IEEE80211_IF_TYPE_AP) return -EINVAL; } else @@ -760,7 +760,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, if (params->vlan && params->vlan != sta->sdata->dev) { vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); - if (vlansdata->vif.type != IEEE80211_IF_TYPE_VLAN || + if (vlansdata->vif.type != IEEE80211_IF_TYPE_VLAN && vlansdata->vif.type != IEEE80211_IF_TYPE_AP) { rcu_read_unlock(); return -EINVAL; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c7314bf..006486b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -899,7 +899,7 @@ extern const struct iw_handler_def ieee80211_iw_handler_def; /* ieee80211_ioctl.c */ -int ieee80211_set_freq(struct ieee80211_local *local, int freq); +int ieee80211_set_freq(struct net_device *dev, int freq); /* ieee80211_sta.c */ void ieee80211_sta_timer(unsigned long data); void ieee80211_sta_work(struct work_struct *work); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 915afad..98c0b5e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -511,6 +511,7 @@ static int ieee80211_stop(struct net_device *dev) case IEEE80211_IF_TYPE_STA: case IEEE80211_IF_TYPE_IBSS: sdata->u.sta.state = IEEE80211_DISABLED; + memset(sdata->u.sta.bssid, 0, ETH_ALEN); del_timer_sync(&sdata->u.sta.timer); /* * When we get here, the interface is marked down. @@ -1313,7 +1314,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, /* * Clear the TX filter mask for this STA when sending the next * packet. If the STA went to power save mode, this will happen - * happen when it wakes up for the next time. + * when it wakes up for the next time. */ sta->flags |= WLAN_STA_CLEAR_PS_FILT; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 4adba09..4d2b582 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -44,7 +44,7 @@ #define IEEE80211_RETRY_AUTH_INTERVAL (1 * HZ) #define IEEE80211_SCAN_INTERVAL (2 * HZ) #define IEEE80211_SCAN_INTERVAL_SLOW (15 * HZ) -#define IEEE80211_IBSS_JOIN_TIMEOUT (20 * HZ) +#define IEEE80211_IBSS_JOIN_TIMEOUT (7 * HZ) #define IEEE80211_PROBE_DELAY (HZ / 33) #define IEEE80211_CHANNEL_TIME (HZ / 33) @@ -730,7 +730,17 @@ static void ieee80211_send_assoc(struct net_device *dev, if (bss->wmm_ie) { wmm = 1; } + + /* get all rates supported by the device and the AP as + * some APs don't like getting a superset of their rates + * in the association request (e.g. D-Link DAP 1353 in + * b-only mode) */ + rates_len = ieee80211_compatible_rates(bss, sband, &rates); + ieee80211_rx_bss_put(dev, bss); + } else { + rates = ~0; + rates_len = sband->n_bitrates; } mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); @@ -761,10 +771,7 @@ static void ieee80211_send_assoc(struct net_device *dev, *pos++ = ifsta->ssid_len; memcpy(pos, ifsta->ssid, ifsta->ssid_len); - /* all supported rates should be added here but some APs - * (e.g. D-Link DAP 1353 in b-only mode) don't like that - * Therefore only add rates the AP supports */ - rates_len = ieee80211_compatible_rates(bss, sband, &rates); + /* add all rates which were marked to be used above */ supp_rates_len = rates_len; if (supp_rates_len > 8) supp_rates_len = 8; @@ -1318,7 +1325,7 @@ static void ieee80211_sta_process_addba_request(struct net_device *dev, /* prepare reordering buffer */ tid_agg_rx->reorder_buf = - kmalloc(buf_size * sizeof(struct sk_buf *), GFP_ATOMIC); + kmalloc(buf_size * sizeof(struct sk_buff *), GFP_ATOMIC); if (!tid_agg_rx->reorder_buf) { if (net_ratelimit()) printk(KERN_ERR "can not allocate reordering buffer " @@ -1327,7 +1334,7 @@ static void ieee80211_sta_process_addba_request(struct net_device *dev, goto end; } memset(tid_agg_rx->reorder_buf, 0, - buf_size * sizeof(struct sk_buf *)); + buf_size * sizeof(struct sk_buff *)); if (local->ops->ampdu_action) ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_START, @@ -1607,7 +1614,7 @@ void sta_addba_resp_timer_expired(unsigned long data) * only one argument, and both sta_info and TID are needed, so init * flow in sta_info_create gives the TID as data, while the timer_to_id * array gives the sta through container_of */ - u16 tid = *(int *)data; + u16 tid = *(u8 *)data; struct sta_info *temp_sta = container_of((void *)data, struct sta_info, timer_to_tid[tid]); @@ -1655,7 +1662,7 @@ timer_expired_exit: void sta_rx_agg_session_timer_expired(unsigned long data) { /* not an elegant detour, but there is no choice as the timer passes - * only one argument, and verious sta_info are needed here, so init + * only one argument, and various sta_info are needed here, so init * flow in sta_info_create gives the TID as data, while the timer_to_id * array gives the sta through container_of */ u8 *ptid = (u8 *)data; @@ -2329,6 +2336,7 @@ static int ieee80211_sta_join_ibss(struct net_device *dev, u8 *pos; struct ieee80211_sub_if_data *sdata; struct ieee80211_supported_band *sband; + union iwreq_data wrqu; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; @@ -2351,13 +2359,10 @@ static int ieee80211_sta_join_ibss(struct net_device *dev, sdata->drop_unencrypted = bss->capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; - res = ieee80211_set_freq(local, bss->freq); + res = ieee80211_set_freq(dev, bss->freq); - if (local->oper_channel->flags & IEEE80211_CHAN_NO_IBSS) { - printk(KERN_DEBUG "%s: IBSS not allowed on frequency " - "%d MHz\n", dev->name, local->oper_channel->center_freq); - return -1; - } + if (res) + return res; /* Set beacon template */ skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400); @@ -2472,7 +2477,9 @@ static int ieee80211_sta_join_ibss(struct net_device *dev, ifsta->state = IEEE80211_IBSS_JOINED; mod_timer(&ifsta->timer, jiffies + IEEE80211_IBSS_MERGE_INTERVAL); - ieee80211_rx_bss_put(dev, bss); + memset(&wrqu, 0, sizeof(wrqu)); + memcpy(wrqu.ap_addr.sa_data, bss->bssid, ETH_ALEN); + wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); return res; } @@ -3446,21 +3453,17 @@ static int ieee80211_sta_config_auth(struct net_device *dev, struct ieee80211_sta_bss *bss, *selected = NULL; int top_rssi = 0, freq; - if (!(ifsta->flags & (IEEE80211_STA_AUTO_SSID_SEL | - IEEE80211_STA_AUTO_BSSID_SEL | IEEE80211_STA_AUTO_CHANNEL_SEL))) { - ifsta->state = IEEE80211_AUTHENTICATE; - ieee80211_sta_reset_auth(dev, ifsta); - return 0; - } - spin_lock_bh(&local->sta_bss_lock); freq = local->oper_channel->center_freq; list_for_each_entry(bss, &local->sta_bss_list, list) { if (!(bss->capability & WLAN_CAPABILITY_ESS)) continue; - if (!!(bss->capability & WLAN_CAPABILITY_PRIVACY) ^ - !!sdata->default_key) + if ((ifsta->flags & (IEEE80211_STA_AUTO_SSID_SEL | + IEEE80211_STA_AUTO_BSSID_SEL | + IEEE80211_STA_AUTO_CHANNEL_SEL)) && + (!!(bss->capability & WLAN_CAPABILITY_PRIVACY) ^ + !!sdata->default_key)) continue; if (!(ifsta->flags & IEEE80211_STA_AUTO_CHANNEL_SEL) && @@ -3485,7 +3488,7 @@ static int ieee80211_sta_config_auth(struct net_device *dev, spin_unlock_bh(&local->sta_bss_lock); if (selected) { - ieee80211_set_freq(local, selected->freq); + ieee80211_set_freq(dev, selected->freq); if (!(ifsta->flags & IEEE80211_STA_SSID_SET)) ieee80211_sta_set_ssid(dev, selected->ssid, selected->ssid_len); @@ -3520,6 +3523,7 @@ static int ieee80211_sta_create_ibss(struct net_device *dev, struct ieee80211_supported_band *sband; u8 bssid[ETH_ALEN], *pos; int i; + int ret; DECLARE_MAC_BUF(mac); #if 0 @@ -3564,7 +3568,9 @@ static int ieee80211_sta_create_ibss(struct net_device *dev, *pos++ = (u8) (rate / 5); } - return ieee80211_sta_join_ibss(dev, ifsta, bss); + ret = ieee80211_sta_join_ibss(dev, ifsta, bss); + ieee80211_rx_bss_put(dev, bss); + return ret; } @@ -3612,10 +3618,13 @@ static int ieee80211_sta_find_ibss(struct net_device *dev, (bss = ieee80211_rx_bss_get(dev, bssid, local->hw.conf.channel->center_freq, ifsta->ssid, ifsta->ssid_len))) { + int ret; printk(KERN_DEBUG "%s: Selected IBSS BSSID %s" " based on configured SSID\n", dev->name, print_mac(mac, bssid)); - return ieee80211_sta_join_ibss(dev, ifsta, bss); + ret = ieee80211_sta_join_ibss(dev, ifsta, bss); + ieee80211_rx_bss_put(dev, bss); + return ret; } #ifdef CONFIG_MAC80211_IBSS_DEBUG printk(KERN_DEBUG " did not try to join ibss\n"); @@ -4092,18 +4101,17 @@ ieee80211_sta_scan_result(struct net_device *dev, memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWFREQ; - iwe.u.freq.m = bss->freq; - iwe.u.freq.e = 6; + iwe.u.freq.m = ieee80211_frequency_to_channel(bss->freq); + iwe.u.freq.e = 0; current_ev = iwe_stream_add_event(current_ev, end_buf, &iwe, IW_EV_FREQ_LEN); memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWFREQ; - iwe.u.freq.m = ieee80211_frequency_to_channel(bss->freq); - iwe.u.freq.e = 0; + iwe.u.freq.m = bss->freq; + iwe.u.freq.e = 6; current_ev = iwe_stream_add_event(current_ev, end_buf, &iwe, IW_EV_FREQ_LEN); - memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVQUAL; iwe.u.qual.qual = bss->signal; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1958bfb..0941e5d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1091,7 +1091,7 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx) u16 fc, hdrlen, ethertype; u8 *payload; u8 dst[ETH_ALEN]; - u8 src[ETH_ALEN]; + u8 src[ETH_ALEN] __aligned(2); struct sk_buff *skb = rx->skb; struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); DECLARE_MAC_BUF(mac); @@ -1234,7 +1234,7 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx) */ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx) { - static const u8 pae_group_addr[ETH_ALEN] + static const u8 pae_group_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xC2, 0x00, 0x00, 0x03 }; struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1d7dd54..c80d589 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1132,7 +1132,7 @@ static int ieee80211_tx(struct net_device *dev, struct sk_buff *skb, ieee80211_tx_handler *handler; struct ieee80211_tx_data tx; ieee80211_tx_result res = TX_DROP, res_prepare; - int ret, i; + int ret, i, retries = 0; WARN_ON(__ieee80211_queue_pending(local, control->queue)); @@ -1216,6 +1216,13 @@ retry: if (!__ieee80211_queue_stopped(local, control->queue)) { clear_bit(IEEE80211_LINK_STATE_PENDING, &local->state[control->queue]); + retries++; + /* + * Driver bug, it's rejecting packets but + * not stopping queues. + */ + if (WARN_ON_ONCE(retries > 5)) + goto drop; goto retry; } memcpy(&store->control, control, @@ -1562,13 +1569,13 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, * be cloned. This could happen, e.g., with Linux bridge code passing * us broadcast frames. */ - if (head_need > 0 || skb_header_cloned(skb)) { + if (head_need > 0 || skb_cloned(skb)) { #if 0 printk(KERN_DEBUG "%s: need to reallocate buffer for %d bytes " "of headroom\n", dev->name, head_need); #endif - if (skb_header_cloned(skb)) + if (skb_cloned(skb)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else I802_DEBUG_INC(local->tx_expand_skb_head); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 24a465c..4e97b26 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -34,11 +34,11 @@ void *mac80211_wiphy_privid = &mac80211_wiphy_privid; /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ -const unsigned char rfc1042_header[] = +const unsigned char rfc1042_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; /* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ -const unsigned char bridge_tunnel_header[] = +const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; @@ -389,6 +389,41 @@ void ieee80211_iterate_active_interfaces( struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; + rtnl_lock(); + + list_for_each_entry(sdata, &local->interfaces, list) { + switch (sdata->vif.type) { + case IEEE80211_IF_TYPE_INVALID: + case IEEE80211_IF_TYPE_MNTR: + case IEEE80211_IF_TYPE_VLAN: + continue; + case IEEE80211_IF_TYPE_AP: + case IEEE80211_IF_TYPE_STA: + case IEEE80211_IF_TYPE_IBSS: + case IEEE80211_IF_TYPE_WDS: + case IEEE80211_IF_TYPE_MESH_POINT: + break; + } + if (sdata->dev == local->mdev) + continue; + if (netif_running(sdata->dev)) + iterator(data, sdata->dev->dev_addr, + &sdata->vif); + } + + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces); + +void ieee80211_iterate_active_interfaces_atomic( + struct ieee80211_hw *hw, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata; + rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) { @@ -413,4 +448,4 @@ void ieee80211_iterate_active_interfaces( rcu_read_unlock(); } -EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces); +EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); diff --git a/net/mac80211/wext.c b/net/mac80211/wext.c index 76e1de1..6106cb7 100644 --- a/net/mac80211/wext.c +++ b/net/mac80211/wext.c @@ -209,7 +209,6 @@ static int ieee80211_ioctl_giwrange(struct net_device *dev, range->num_frequency = c; IW_EVENT_CAPA_SET_KERNEL(range->event_capa); - IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWTHRSPY); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWAP); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWSCAN); @@ -291,14 +290,22 @@ static int ieee80211_ioctl_giwmode(struct net_device *dev, return 0; } -int ieee80211_set_freq(struct ieee80211_local *local, int freqMHz) +int ieee80211_set_freq(struct net_device *dev, int freqMHz) { int ret = -EINVAL; struct ieee80211_channel *chan; + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); chan = ieee80211_get_channel(local->hw.wiphy, freqMHz); if (chan && !(chan->flags & IEEE80211_CHAN_DISABLED)) { + if (sdata->vif.type == IEEE80211_IF_TYPE_IBSS && + chan->flags & IEEE80211_CHAN_NO_IBSS) { + printk(KERN_DEBUG "%s: IBSS not allowed on frequency " + "%d MHz\n", dev->name, chan->center_freq); + return ret; + } local->oper_channel = chan; if (local->sta_sw_scanning || local->sta_hw_scanning) @@ -316,7 +323,6 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == IEEE80211_IF_TYPE_STA) @@ -330,14 +336,14 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev, IEEE80211_STA_AUTO_CHANNEL_SEL; return 0; } else - return ieee80211_set_freq(local, + return ieee80211_set_freq(dev, ieee80211_channel_to_frequency(freq->m)); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) div /= 10; if (div > 0) - return ieee80211_set_freq(local, freq->m / div); + return ieee80211_set_freq(dev, freq->m / div); else return -EINVAL; } @@ -490,9 +496,15 @@ static int ieee80211_ioctl_giwap(struct net_device *dev, sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == IEEE80211_IF_TYPE_STA || sdata->vif.type == IEEE80211_IF_TYPE_IBSS) { - ap_addr->sa_family = ARPHRD_ETHER; - memcpy(&ap_addr->sa_data, sdata->u.sta.bssid, ETH_ALEN); - return 0; + if (sdata->u.sta.state == IEEE80211_ASSOCIATED || + sdata->u.sta.state == IEEE80211_IBSS_JOINED) { + ap_addr->sa_family = ARPHRD_ETHER; + memcpy(&ap_addr->sa_data, sdata->u.sta.bssid, ETH_ALEN); + return 0; + } else { + memset(&ap_addr->sa_data, 0, ETH_ALEN); + return 0; + } } else if (sdata->vif.type == IEEE80211_IF_TYPE_WDS) { ap_addr->sa_family = ARPHRD_ETHER; memcpy(&ap_addr->sa_data, sdata->u.wds.remote_addr, ETH_ALEN); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index dc1598b..635b996 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -673,7 +673,7 @@ int ieee80211_ht_agg_queue_add(struct ieee80211_local *local, #ifdef CONFIG_MAC80211_HT_DEBUG if (net_ratelimit()) printk(KERN_DEBUG "allocated aggregation queue" - " %d tid %d addr %s pool=0x%lX", + " %d tid %d addr %s pool=0x%lX\n", i, tid, print_mac(mac, sta->addr), q->qdisc_pool[0]); #endif /* CONFIG_MAC80211_HT_DEBUG */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4b1799..662c1cc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -196,8 +196,6 @@ destroy_conntrack(struct nf_conntrack *nfct) if (l4proto && l4proto->destroy) l4proto->destroy(ct); - nf_ct_ext_destroy(ct); - rcu_read_unlock(); spin_lock_bh(&nf_conntrack_lock); @@ -520,6 +518,7 @@ static void nf_conntrack_free_rcu(struct rcu_head *head) void nf_conntrack_free(struct nf_conn *ct) { + nf_ct_ext_destroy(ct); call_rcu(&ct->rcu, nf_conntrack_free_rcu); } EXPORT_SYMBOL_GPL(nf_conntrack_free); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e31beeb..e8f0dea 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -587,10 +587,10 @@ int __init nf_conntrack_expect_init(void) return 0; err3: + kmem_cache_destroy(nf_ct_expect_cachep); +err2: nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_vmalloc, nf_ct_expect_hsize); -err2: - kmem_cache_destroy(nf_ct_expect_cachep); err1: return err; } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index bcc19fa..8a3f8b3 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -59,12 +59,19 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) if (!*ext) return NULL; + INIT_RCU_HEAD(&(*ext)->rcu); (*ext)->offset[id] = off; (*ext)->len = len; return (void *)(*ext) + off; } +static void __nf_ct_ext_free_rcu(struct rcu_head *head) +{ + struct nf_ct_ext *ext = container_of(head, struct nf_ct_ext, rcu); + kfree(ext); +} + void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) { struct nf_ct_ext *new; @@ -106,7 +113,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) (void *)ct->ext + ct->ext->offset[i]); rcu_read_unlock(); } - kfree(ct->ext); + call_rcu(&ct->ext->rcu, __nf_ct_ext_free_rcu); ct->ext = new; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 95da1a2..2f83c15 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -619,6 +619,7 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = { static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = { .name = "H.245", .me = THIS_MODULE, + .tuple.src.l3num = AF_UNSPEC, .tuple.dst.protonum = IPPROTO_UDP, .help = h245_help, .expect_policy = &h245_exp_policy, @@ -1765,6 +1766,7 @@ static void __exit nf_conntrack_h323_fini(void) nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); kfree(h323_buffer); pr_debug("nf_ct_h323: fini\n"); } @@ -1777,28 +1779,34 @@ static int __init nf_conntrack_h323_init(void) h323_buffer = kmalloc(65536, GFP_KERNEL); if (!h323_buffer) return -ENOMEM; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245); if (ret < 0) goto err1; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]); if (ret < 0) goto err2; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]); if (ret < 0) goto err3; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]); if (ret < 0) goto err4; + ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]); + if (ret < 0) + goto err5; pr_debug("nf_ct_h323: init success\n"); return 0; -err4: +err5: nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); -err3: +err4: nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); -err2: +err3: nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); +err2: + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); err1: + kfree(h323_buffer); return ret; } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index bc11d70..9fda6ee 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -92,10 +92,6 @@ void nf_log_packet(int pf, vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(pf, hooknum, skb, in, out, loginfo, prefix); - } else if (net_ratelimit()) { - printk(KERN_WARNING "nf_log_packet: can\'t log since " - "no backend logging module loaded in! Please either " - "load one, or disable logging explicitly\n"); } rcu_read_unlock(); } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 2e89a00..70907f6 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -73,7 +73,8 @@ connlimit_iphash6(const union nf_inet_addr *addr, static inline bool already_closed(const struct nf_conn *conn) { if (nf_ct_protonum(conn) == IPPROTO_TCP) - return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT; + return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT || + conn->proto.tcp.state == TCP_CONNTRACK_CLOSE; else return 0; } diff --git a/net/netlink/attr.c b/net/netlink/attr.c index feb326f..47bbf45 100644 --- a/net/netlink/attr.c +++ b/net/netlink/attr.c @@ -400,13 +400,13 @@ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) - return -1; + return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; @@ -418,13 +418,13 @@ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -1; + return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; @@ -436,13 +436,13 @@ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -1; + return -EMSGSIZE; memcpy(skb_put(skb, attrlen), data, attrlen); return 0; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d16929c..3e1191c 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -444,8 +444,11 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (ops->dumpit == NULL) return -EOPNOTSUPP; - return netlink_dump_start(genl_sock, skb, nlh, - ops->dumpit, ops->done); + genl_unlock(); + err = netlink_dump_start(genl_sock, skb, nlh, + ops->dumpit, ops->done); + genl_lock(); + return err; } if (ops->doit == NULL) @@ -554,7 +557,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, return genlmsg_end(skb, hdr); nla_put_failure: - return genlmsg_cancel(skb, hdr); + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; } static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, @@ -590,7 +594,8 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, return genlmsg_end(skb, hdr); nla_put_failure: - return genlmsg_cancel(skb, hdr); + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; } static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) @@ -601,9 +606,6 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; - if (chains_to_skip != 0) - genl_lock(); - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { if (i < chains_to_skip) continue; @@ -621,9 +623,6 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) } errout: - if (chains_to_skip != 0) - genl_unlock(); - cb->args[0] = i; cb->args[1] = n; @@ -768,7 +767,7 @@ static int __init genl_init(void) /* we'll bump the group number right afterwards */ genl_sock = netlink_kernel_create(&init_net, NETLINK_GENERIC, 0, - genl_rcv, NULL, THIS_MODULE); + genl_rcv, &genl_mutex, THIS_MODULE); if (genl_sock == NULL) panic("GENL: Cannot initialize generic netlink\n"); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 1086df7..9360fc8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -220,7 +220,7 @@ replay: tp = kzalloc(sizeof(*tp), GFP_KERNEL); if (tp == NULL) goto errout; - err = -EINVAL; + err = -ENOENT; tp_ops = tcf_proto_lookup_ops(tca[TCA_KIND]); if (tp_ops == NULL) { #ifdef CONFIG_KMOD diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0df911f..64465ba 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -444,7 +444,8 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -466,7 +467,8 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static const struct Qdisc_class_ops dsmark_class_ops = { diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 3a9d226..c89fba5 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -582,7 +582,8 @@ append_opt: return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static void gred_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 87293d0..fdfaa3f 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1360,7 +1360,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, nla_put_failure: nla_nest_cancel(skb, nest); - return -1; + return -EMSGSIZE; } static int diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 5bc1ed4..6807c97 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -28,6 +28,7 @@ * $Id: sch_htb.c,v 1.25 2003/12/07 11:08:25 devik Exp devik $ */ #include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> @@ -53,13 +54,17 @@ */ #define HTB_HSIZE 16 /* classid hash size */ -#define HTB_HYSTERESIS 1 /* whether to use mode hysteresis for speedup */ +static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */ #define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ #if HTB_VER >> 16 != TC_HTB_PROTOVER #error "Mismatched sch_htb.c and pkt_sch.h" #endif +/* Module parameter and sysfs export */ +module_param (htb_hysteresis, int, 0640); +MODULE_PARM_DESC(htb_hysteresis, "Hysteresis mode, less CPU load, less accurate"); + /* used internaly to keep status of single class */ enum htb_cmode { HTB_CANT_SEND, /* class can't send and can't borrow */ @@ -462,19 +467,21 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) htb_remove_class_from_row(q, cl, mask); } -#if HTB_HYSTERESIS static inline long htb_lowater(const struct htb_class *cl) { - return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0; + if (htb_hysteresis) + return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0; + else + return 0; } static inline long htb_hiwater(const struct htb_class *cl) { - return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0; + if (htb_hysteresis) + return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0; + else + return 0; } -#else -#define htb_lowater(cl) (0) -#define htb_hiwater(cl) (0) -#endif + /** * htb_class_mode - computes and returns current class mode diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 3dcd493..5c56985 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -281,7 +281,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b4cd2b7..024c3eb 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -474,6 +474,15 @@ static void sctp_association_destroy(struct sctp_association *asoc) void sctp_assoc_set_primary(struct sctp_association *asoc, struct sctp_transport *transport) { + int changeover = 0; + + /* it's a changeover only if we already have a primary path + * that we are changing + */ + if (asoc->peer.primary_path != NULL && + asoc->peer.primary_path != transport) + changeover = 1 ; + asoc->peer.primary_path = transport; /* Set a default msg_name for events. */ @@ -499,12 +508,12 @@ void sctp_assoc_set_primary(struct sctp_association *asoc, * double switch to the same destination address. */ if (transport->cacc.changeover_active) - transport->cacc.cycling_changeover = 1; + transport->cacc.cycling_changeover = changeover; /* 2) The sender MUST set CHANGEOVER_ACTIVE to indicate that * a changeover has occurred. */ - transport->cacc.changeover_active = 1; + transport->cacc.changeover_active = changeover; /* 3) The sender MUST store the next TSN to be sent in * next_tsn_at_change. @@ -1203,6 +1212,9 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) struct list_head *head = &asoc->peer.transport_addr_list; struct list_head *pos; + if (asoc->peer.transport_count == 1) + return; + /* Find the next transport in a round-robin fashion. */ t = asoc->peer.retran_path; pos = &t->transports; @@ -1217,6 +1229,15 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) t = list_entry(pos, struct sctp_transport, transports); + /* We have exhausted the list, but didn't find any + * other active transports. If so, use the next + * transport. + */ + if (t == asoc->peer.retran_path) { + t = next; + break; + } + /* Try to find an active transport. */ if ((t->state == SCTP_ACTIVE) || @@ -1229,15 +1250,6 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) if (!next) next = t; } - - /* We have exhausted the list, but didn't find any - * other active transports. If so, use the next - * transport. - */ - if (t == asoc->peer.retran_path) { - t = next; - break; - } } asoc->peer.retran_path = t; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e45e44c..a2f4d4d 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -299,7 +299,8 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1, /* Fills in the source address(saddr) based on the destination address(daddr) * and asoc's bind address list. */ -static void sctp_v6_get_saddr(struct sctp_association *asoc, +static void sctp_v6_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -318,7 +319,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, if (!asoc) { ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, &daddr->v6.sin6_addr, - inet6_sk(asoc->base.sk)->srcprefs, + inet6_sk(&sk->inet.sk)->srcprefs, &saddr->v6.sin6_addr); SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); @@ -726,6 +727,11 @@ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr)); } +static void sctp_v6_ecn_capable(struct sock *sk) +{ + inet6_sk(sk)->tclass |= INET_ECN_ECT_0; +} + /* Initialize a PF_INET6 socket msg_name. */ static void sctp_inet6_msgname(char *msgname, int *addr_len) { @@ -996,6 +1002,7 @@ static struct sctp_af sctp_af_inet6 = { .skb_iif = sctp_v6_skb_iif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, + .ecn_capable = sctp_v6_ecn_capable, .net_header_len = sizeof(struct ipv6hdr), .sockaddr_len = sizeof(struct sockaddr_in6), #ifdef CONFIG_COMPAT diff --git a/net/sctp/output.c b/net/sctp/output.c index cf4f9fb..6d45bae 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -548,7 +548,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - INET_ECN_xmit(nskb->sk); + (*tp->af_specific->ecn_capable)(nskb->sk); /* Set up the IP options. */ /* BUG: not implemented diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 59edfd2..ace6770 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -208,6 +208,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + q->fast_rtx = 0; q->outstanding_bytes = 0; q->empty = 1; q->cork = 0; @@ -500,6 +501,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); + q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); @@ -518,9 +520,15 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by * following the procedures outlined in C1 - C5. */ - sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point); + if (reason == SCTP_RTXR_T3_RTX) + sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point); - error = sctp_outq_flush(q, /* rtx_timeout */ 1); + /* Flush the queues only on timeout, since fast_rtx is only + * triggered during sack processing and the queue + * will be flushed at the end. + */ + if (reason != SCTP_RTXR_FAST_RTX) + error = sctp_outq_flush(q, /* rtx_timeout */ 1); if (error) q->asoc->base.sk->sk_err = -error; @@ -538,17 +546,23 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer) { struct list_head *lqueue; - struct list_head *lchunk; struct sctp_transport *transport = pkt->transport; sctp_xmit_t status; struct sctp_chunk *chunk, *chunk1; struct sctp_association *asoc; + int fast_rtx; int error = 0; + int timer = 0; + int done = 0; asoc = q->asoc; lqueue = &q->retransmit; + fast_rtx = q->fast_rtx; - /* RFC 2960 6.3.3 Handle T3-rtx Expiration + /* This loop handles time-out retransmissions, fast retransmissions, + * and retransmissions due to opening of whindow. + * + * RFC 2960 6.3.3 Handle T3-rtx Expiration * * E3) Determine how many of the earliest (i.e., lowest TSN) * outstanding DATA chunks for the address for which the @@ -563,12 +577,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, * [Just to be painfully clear, if we are retransmitting * because a timeout just happened, we should send only ONE * packet of retransmitted data.] + * + * For fast retransmissions we also send only ONE packet. However, + * if we are just flushing the queue due to open window, we'll + * try to send as much as possible. */ - lchunk = sctp_list_dequeue(lqueue); - - while (lchunk) { - chunk = list_entry(lchunk, struct sctp_chunk, - transmitted_list); + list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the @@ -576,58 +590,60 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, * next chunk. */ if (chunk->tsn_gap_acked) { - list_add_tail(lchunk, &transport->transmitted); - lchunk = sctp_list_dequeue(lqueue); + list_del(&chunk->transmitted_list); + list_add_tail(&chunk->transmitted_list, + &transport->transmitted); continue; } + /* If we are doing fast retransmit, ignore non-fast_rtransmit + * chunks + */ + if (fast_rtx && !chunk->fast_retransmit) + continue; + /* Attempt to append this chunk to the packet. */ status = sctp_packet_append_chunk(pkt, chunk); switch (status) { case SCTP_XMIT_PMTU_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* If we are retransmitting, we should only * send a single packet. */ - if (rtx_timeout) { - list_add(lchunk, lqueue); - lchunk = NULL; - } + if (rtx_timeout || fast_rtx) + done = 1; - /* Bundle lchunk in the next round. */ + /* Bundle next chunk in the next round. */ break; case SCTP_XMIT_RWND_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA as there is no more room * at the receiver. */ - list_add(lchunk, lqueue); - lchunk = NULL; + done = 1; break; case SCTP_XMIT_NAGLE_DELAY: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA because of nagle delay. */ - list_add(lchunk, lqueue); - lchunk = NULL; + done = 1; break; default: /* The append was successful, so add this chunk to * the transmitted list. */ - list_add_tail(lchunk, &transport->transmitted); + list_del(&chunk->transmitted_list); + list_add_tail(&chunk->transmitted_list, + &transport->transmitted); /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. @@ -635,27 +651,44 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->fast_retransmit > 0) chunk->fast_retransmit = -1; - *start_timer = 1; - q->empty = 0; + /* Force start T3-rtx timer when fast retransmitting + * the earliest outstanding TSN + */ + if (!timer && fast_rtx && + ntohl(chunk->subh.data_hdr->tsn) == + asoc->ctsn_ack_point + 1) + timer = 2; - /* Retrieve a new chunk to bundle. */ - lchunk = sctp_list_dequeue(lqueue); + q->empty = 0; break; } - /* If we are here due to a retransmit timeout or a fast - * retransmit and if there are any chunks left in the retransmit - * queue that could not fit in the PMTU sized packet, they need - * to be marked as ineligible for a subsequent fast retransmit. - */ - if (rtx_timeout && !lchunk) { - list_for_each_entry(chunk1, lqueue, transmitted_list) { - if (chunk1->fast_retransmit > 0) - chunk1->fast_retransmit = -1; - } + /* Set the timer if there were no errors */ + if (!error && !timer) + timer = 1; + + if (done) + break; + } + + /* If we are here due to a retransmit timeout or a fast + * retransmit and if there are any chunks left in the retransmit + * queue that could not fit in the PMTU sized packet, they need + * to be marked as ineligible for a subsequent fast retransmit. + */ + if (rtx_timeout || fast_rtx) { + list_for_each_entry(chunk1, lqueue, transmitted_list) { + if (chunk1->fast_retransmit > 0) + chunk1->fast_retransmit = -1; } } + *start_timer = timer; + + /* Clear fast retransmit hint */ + if (fast_rtx) + q->fast_rtx = 0; + return error; } @@ -862,7 +895,8 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) rtx_timeout, &start_timer); if (start_timer) - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, + start_timer-1); /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. @@ -977,7 +1011,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) list_add_tail(&chunk->transmitted_list, &transport->transmitted); - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, start_timer-1); q->empty = 0; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 0ec234b..9258dfe 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -108,14 +108,23 @@ static __init int sctp_proc_init(void) } if (sctp_snmp_proc_init()) - goto out_nomem; + goto out_snmp_proc_init; if (sctp_eps_proc_init()) - goto out_nomem; + goto out_eps_proc_init; if (sctp_assocs_proc_init()) - goto out_nomem; + goto out_assocs_proc_init; return 0; +out_assocs_proc_init: + sctp_eps_proc_exit(); +out_eps_proc_init: + sctp_snmp_proc_exit(); +out_snmp_proc_init: + if (proc_net_sctp) { + proc_net_sctp = NULL; + remove_proc_entry("sctp", init_net.proc_net); + } out_nomem: return -ENOMEM; } @@ -470,11 +479,11 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ + sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) continue; - sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a)) goto out_unlock; } @@ -519,7 +528,8 @@ out: /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ -static void sctp_v4_get_saddr(struct sctp_association *asoc, +static void sctp_v4_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -616,6 +626,11 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr)); } +static void sctp_v4_ecn_capable(struct sock *sk) +{ + INET_ECN_xmit(sk); +} + /* Event handler for inet address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same @@ -934,6 +949,7 @@ static struct sctp_af sctp_af_inet = { .skb_iif = sctp_v4_skb_iif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, + .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), #ifdef CONFIG_COMPAT diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e7e3baf..0dbcde6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4401,7 +4401,9 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, if (copy_from_user(&getaddrs, optval, len)) return -EFAULT; - if (getaddrs.addr_num <= 0) return -EINVAL; + if (getaddrs.addr_num <= 0 || + getaddrs.addr_num >= (INT_MAX / sizeof(union sctp_addr))) + return -EINVAL; /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound diff --git a/net/sctp/transport.c b/net/sctp/transport.c index f4938f6..3f34f61 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -79,6 +79,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; + peer->fast_recovery = 0; peer->last_time_heard = jiffies; peer->last_time_used = jiffies; @@ -190,7 +191,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport) /* Start T3_rtx timer if it is not already running and update the heartbeat * timer. This routine is called every time a DATA chunk is sent. */ -void sctp_transport_reset_timers(struct sctp_transport *transport) +void sctp_transport_reset_timers(struct sctp_transport *transport, int force) { /* RFC 2960 6.3.2 Retransmission Timer Rules * @@ -200,7 +201,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport) * address. */ - if (!timer_pending(&transport->T3_rtx_timer)) + if (force || !timer_pending(&transport->T3_rtx_timer)) if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); @@ -291,7 +292,7 @@ void sctp_transport_route(struct sctp_transport *transport, if (saddr) memcpy(&transport->saddr, saddr, sizeof(union sctp_addr)); else - af->get_saddr(asoc, dst, daddr, &transport->saddr); + af->get_saddr(opt, asoc, dst, daddr, &transport->saddr); transport->dst = dst; if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { @@ -403,11 +404,16 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, cwnd = transport->cwnd; flight_size = transport->flight_size; + /* See if we need to exit Fast Recovery first */ + if (transport->fast_recovery && + TSN_lte(transport->fast_recovery_exit, sack_ctsn)) + transport->fast_recovery = 0; + /* The appropriate cwnd increase algorithm is performed if, and only - * if the cumulative TSN has advanced and the congestion window is + * if the cumulative TSN whould advanced and the congestion window is * being fully utilized. */ - if ((transport->asoc->ctsn_ack_point >= sack_ctsn) || + if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) || (flight_size < cwnd)) return; @@ -416,17 +422,23 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, pmtu = transport->asoc->pathmtu; if (cwnd <= ssthresh) { - /* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less - * than or equal to ssthresh an SCTP endpoint MUST use the - * slow start algorithm to increase cwnd only if the current - * congestion window is being fully utilized and an incoming - * SACK advances the Cumulative TSN Ack Point. Only when these - * two conditions are met can the cwnd be increased otherwise - * the cwnd MUST not be increased. If these conditions are met - * then cwnd MUST be increased by at most the lesser of - * 1) the total size of the previously outstanding DATA - * chunk(s) acknowledged, and 2) the destination's path MTU. + /* RFC 4960 7.2.1 + * o When cwnd is less than or equal to ssthresh, an SCTP + * endpoint MUST use the slow-start algorithm to increase + * cwnd only if the current congestion window is being fully + * utilized, an incoming SACK advances the Cumulative TSN + * Ack Point, and the data sender is not in Fast Recovery. + * Only when these three conditions are met can the cwnd be + * increased; otherwise, the cwnd MUST not be increased. + * If these conditions are met, then cwnd MUST be increased + * by, at most, the lesser of 1) the total size of the + * previously outstanding DATA chunk(s) acknowledged, and + * 2) the destination's path MTU. This upper bound protects + * against the ACK-Splitting attack outlined in [SAVAGE99]. */ + if (transport->fast_recovery) + return; + if (bytes_acked > pmtu) cwnd += pmtu; else @@ -502,6 +514,13 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * cwnd = ssthresh * partial_bytes_acked = 0 */ + if (transport->fast_recovery) + return; + + /* Mark Fast recovery */ + transport->fast_recovery = 1; + transport->fast_recovery_exit = transport->asoc->next_tsn - 1; + transport->ssthresh = max(transport->cwnd/2, 4*transport->asoc->pathmtu); transport->cwnd = transport->ssthresh; @@ -586,6 +605,7 @@ void sctp_transport_reset(struct sctp_transport *t) t->flight_size = 0; t->error_count = 0; t->rto_pending = 0; + t->fast_recovery = 0; /* Initialize the state information for SFR-CACC */ t->cacc.changeover_active = 0; diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index d927d9f..744b79f 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -17,8 +17,8 @@ # define RPCDBG_FACILITY RPCDBG_AUTH #endif -#define RPC_ANONYMOUS_USERID ((uid_t)-2) -#define RPC_ANONYMOUS_GROUPID ((gid_t)-2) +#define RPC_MACHINE_CRED_USERID ((uid_t)0) +#define RPC_MACHINE_CRED_GROUPID ((gid_t)0) struct generic_cred { struct rpc_cred gc_base; @@ -44,8 +44,8 @@ EXPORT_SYMBOL_GPL(rpc_lookup_cred); struct rpc_cred *rpc_lookup_machine_cred(void) { struct auth_cred acred = { - .uid = RPC_ANONYMOUS_USERID, - .gid = RPC_ANONYMOUS_GROUPID, + .uid = RPC_MACHINE_CRED_USERID, + .gid = RPC_MACHINE_CRED_GROUPID, .machine_cred = 1, }; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d8e8d79..e46c825 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -6,30 +6,9 @@ #include <linux/sched.h> #include <linux/errno.h> -#include <linux/fcntl.h> -#include <linux/net.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/udp.h> -#include <linux/tcp.h> -#include <linux/unistd.h> -#include <linux/slab.h> -#include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <linux/file.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <net/sock.h> -#include <net/checksum.h> -#include <net/ip.h> -#include <net/ipv6.h> -#include <net/tcp_states.h> -#include <linux/uaccess.h> -#include <asm/ioctls.h> - -#include <linux/sunrpc/types.h> -#include <linux/sunrpc/clnt.h> -#include <linux/sunrpc/xdr.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svc_xprt.h> @@ -296,8 +275,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) if (!(xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED)))) return; - if (test_bit(XPT_DEAD, &xprt->xpt_flags)) - return; cpu = get_cpu(); pool = svc_pool_for_cpu(xprt->xpt_server, cpu); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 3f30ee6..f24800f 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -278,7 +278,7 @@ static int ip_map_show(struct seq_file *m, dom = im->m_client->h.name; if (ipv6_addr_v4mapped(&addr)) { - seq_printf(m, "%s" NIPQUAD_FMT "%s\n", + seq_printf(m, "%s " NIPQUAD_FMT " %s\n", im->m_class, ntohl(addr.s6_addr32[3]) >> 24 & 0xff, ntohl(addr.s6_addr32[3]) >> 16 & 0xff, @@ -286,7 +286,7 @@ static int ip_map_show(struct seq_file *m, ntohl(addr.s6_addr32[3]) >> 0 & 0xff, dom); } else { - seq_printf(m, "%s" NIP6_FMT "%s\n", + seq_printf(m, "%s " NIP6_FMT " %s\n", im->m_class, NIP6(addr), dom); } return 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 88c0ca2..8710117 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -69,6 +69,10 @@ atomic_t rdma_stat_rq_prod; atomic_t rdma_stat_sq_poll; atomic_t rdma_stat_sq_prod; +/* Temporary NFS request map and context caches */ +struct kmem_cache *svc_rdma_map_cachep; +struct kmem_cache *svc_rdma_ctxt_cachep; + /* * This function implements reading and resetting an atomic_t stat * variable through read/write to a proc file. Any write to the file @@ -236,11 +240,14 @@ static ctl_table svcrdma_root_table[] = { void svc_rdma_cleanup(void) { dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n"); + flush_scheduled_work(); if (svcrdma_table_header) { unregister_sysctl_table(svcrdma_table_header); svcrdma_table_header = NULL; } svc_unreg_xprt_class(&svc_rdma_class); + kmem_cache_destroy(svc_rdma_map_cachep); + kmem_cache_destroy(svc_rdma_ctxt_cachep); } int svc_rdma_init(void) @@ -255,9 +262,37 @@ int svc_rdma_init(void) svcrdma_table_header = register_sysctl_table(svcrdma_root_table); + /* Create the temporary map cache */ + svc_rdma_map_cachep = kmem_cache_create("svc_rdma_map_cache", + sizeof(struct svc_rdma_req_map), + 0, + SLAB_HWCACHE_ALIGN, + NULL); + if (!svc_rdma_map_cachep) { + printk(KERN_INFO "Could not allocate map cache.\n"); + goto err0; + } + + /* Create the temporary context cache */ + svc_rdma_ctxt_cachep = + kmem_cache_create("svc_rdma_ctxt_cache", + sizeof(struct svc_rdma_op_ctxt), + 0, + SLAB_HWCACHE_ALIGN, + NULL); + if (!svc_rdma_ctxt_cachep) { + printk(KERN_INFO "Could not allocate WR ctxt cache.\n"); + goto err1; + } + /* Register RDMA with the SVC transport switch */ svc_reg_xprt_class(&svc_rdma_class); return 0; + err1: + kmem_cache_destroy(svc_rdma_map_cachep); + err0: + unregister_sysctl_table(svcrdma_table_header); + return -ENOMEM; } MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>"); MODULE_DESCRIPTION("SVC RDMA Transport"); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index c22d6b6..b4b17f4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -112,11 +112,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -struct chunk_sge { - int start; /* sge no for this chunk */ - int count; /* sge count for this chunk */ -}; - /* Encode a read-chunk-list as an array of IB SGE * * Assumptions: @@ -134,8 +129,8 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head, struct rpcrdma_msg *rmsgp, - struct ib_sge *sge, - struct chunk_sge *ch_sge_ary, + struct svc_rdma_req_map *rpl_map, + struct svc_rdma_req_map *chl_map, int ch_count, int byte_count) { @@ -156,22 +151,18 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, head->arg.head[0] = rqstp->rq_arg.head[0]; head->arg.tail[0] = rqstp->rq_arg.tail[0]; head->arg.pages = &head->pages[head->count]; - head->sge[0].length = head->count; /* save count of hdr pages */ + head->hdr_count = head->count; /* save count of hdr pages */ head->arg.page_base = 0; head->arg.page_len = ch_bytes; head->arg.len = rqstp->rq_arg.len + ch_bytes; head->arg.buflen = rqstp->rq_arg.buflen + ch_bytes; head->count++; - ch_sge_ary[0].start = 0; + chl_map->ch[0].start = 0; while (byte_count) { + rpl_map->sge[sge_no].iov_base = + page_address(rqstp->rq_arg.pages[page_no]) + page_off; sge_bytes = min_t(int, PAGE_SIZE-page_off, ch_bytes); - sge[sge_no].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - rqstp->rq_arg.pages[page_no], - page_off, sge_bytes, - DMA_FROM_DEVICE); - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + rpl_map->sge[sge_no].iov_len = sge_bytes; /* * Don't bump head->count here because the same page * may be used by multiple SGE. @@ -187,11 +178,11 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, * SGE, move to the next SGE */ if (ch_bytes == 0) { - ch_sge_ary[ch_no].count = - sge_no - ch_sge_ary[ch_no].start; + chl_map->ch[ch_no].count = + sge_no - chl_map->ch[ch_no].start; ch_no++; ch++; - ch_sge_ary[ch_no].start = sge_no; + chl_map->ch[ch_no].start = sge_no; ch_bytes = ch->rc_target.rs_length; /* If bytes remaining account for next chunk */ if (byte_count) { @@ -220,18 +211,25 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, return sge_no; } -static void rdma_set_ctxt_sge(struct svc_rdma_op_ctxt *ctxt, - struct ib_sge *sge, +static void rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, + struct svc_rdma_op_ctxt *ctxt, + struct kvec *vec, u64 *sgl_offset, int count) { int i; ctxt->count = count; + ctxt->direction = DMA_FROM_DEVICE; for (i = 0; i < count; i++) { - ctxt->sge[i].addr = sge[i].addr; - ctxt->sge[i].length = sge[i].length; - *sgl_offset = *sgl_offset + sge[i].length; + atomic_inc(&xprt->sc_dma_used); + ctxt->sge[i].addr = + ib_dma_map_single(xprt->sc_cm_id->device, + vec[i].iov_base, vec[i].iov_len, + DMA_FROM_DEVICE); + ctxt->sge[i].length = vec[i].iov_len; + ctxt->sge[i].lkey = xprt->sc_phys_mr->lkey; + *sgl_offset = *sgl_offset + vec[i].iov_len; } } @@ -260,11 +258,16 @@ static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) * On our side, we need to read into a pagelist. The first page immediately * follows the RPC header. * - * This function returns 1 to indicate success. The data is not yet in + * This function returns: + * 0 - No error and no read-list found. + * + * 1 - Successful read-list processing. The data is not yet in * the pagelist and therefore the RPC request must be deferred. The * I/O completion will enqueue the transport again and * svc_rdma_recvfrom will complete the request. * + * <0 - Error processing/posting read-list. + * * NOTE: The ctxt must not be touched after the last WR has been posted * because the I/O completion processing may occur on another * processor and free / modify the context. Ne touche pas! @@ -277,50 +280,38 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt, struct ib_send_wr read_wr; int err = 0; int ch_no; - struct ib_sge *sge; int ch_count; int byte_count; int sge_count; u64 sgl_offset; struct rpcrdma_read_chunk *ch; struct svc_rdma_op_ctxt *ctxt = NULL; - struct svc_rdma_op_ctxt *head; - struct svc_rdma_op_ctxt *tmp_sge_ctxt; - struct svc_rdma_op_ctxt *tmp_ch_ctxt; - struct chunk_sge *ch_sge_ary; + struct svc_rdma_req_map *rpl_map; + struct svc_rdma_req_map *chl_map; /* If no read list is present, return 0 */ ch = svc_rdma_get_read_chunk(rmsgp); if (!ch) return 0; - /* Allocate temporary contexts to keep SGE */ - BUG_ON(sizeof(struct ib_sge) < sizeof(struct chunk_sge)); - tmp_sge_ctxt = svc_rdma_get_context(xprt); - sge = tmp_sge_ctxt->sge; - tmp_ch_ctxt = svc_rdma_get_context(xprt); - ch_sge_ary = (struct chunk_sge *)tmp_ch_ctxt->sge; + /* Allocate temporary reply and chunk maps */ + rpl_map = svc_rdma_get_req_map(); + chl_map = svc_rdma_get_req_map(); svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count); + if (ch_count > RPCSVC_MAXPAGES) + return -EINVAL; sge_count = rdma_rcl_to_sge(xprt, rqstp, hdr_ctxt, rmsgp, - sge, ch_sge_ary, + rpl_map, chl_map, ch_count, byte_count); - head = svc_rdma_get_context(xprt); sgl_offset = 0; ch_no = 0; for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; ch->rc_discrim != 0; ch++, ch_no++) { next_sge: - if (!ctxt) - ctxt = head; - else { - ctxt->next = svc_rdma_get_context(xprt); - ctxt = ctxt->next; - } - ctxt->next = NULL; + ctxt = svc_rdma_get_context(xprt); ctxt->direction = DMA_FROM_DEVICE; - clear_bit(RDMACTXT_F_READ_DONE, &ctxt->flags); clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); /* Prepare READ WR */ @@ -333,50 +324,46 @@ next_sge: read_wr.wr.rdma.remote_addr = get_unaligned(&(ch->rc_target.rs_offset)) + sgl_offset; - read_wr.sg_list = &sge[ch_sge_ary[ch_no].start]; + read_wr.sg_list = ctxt->sge; read_wr.num_sge = - rdma_read_max_sge(xprt, ch_sge_ary[ch_no].count); - rdma_set_ctxt_sge(ctxt, &sge[ch_sge_ary[ch_no].start], + rdma_read_max_sge(xprt, chl_map->ch[ch_no].count); + rdma_set_ctxt_sge(xprt, ctxt, + &rpl_map->sge[chl_map->ch[ch_no].start], &sgl_offset, read_wr.num_sge); if (((ch+1)->rc_discrim == 0) && - (read_wr.num_sge == ch_sge_ary[ch_no].count)) { + (read_wr.num_sge == chl_map->ch[ch_no].count)) { /* * Mark the last RDMA_READ with a bit to * indicate all RPC data has been fetched from * the client and the RPC needs to be enqueued. */ set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - ctxt->next = hdr_ctxt; - hdr_ctxt->next = head; + ctxt->read_hdr = hdr_ctxt; } /* Post the read */ err = svc_rdma_send(xprt, &read_wr); if (err) { - printk(KERN_ERR "svcrdma: Error posting send = %d\n", + printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n", err); - /* - * Break the circular list so free knows when - * to stop if the error happened to occur on - * the last read - */ - ctxt->next = NULL; + set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + svc_rdma_put_context(ctxt, 0); goto out; } atomic_inc(&rdma_stat_read); - if (read_wr.num_sge < ch_sge_ary[ch_no].count) { - ch_sge_ary[ch_no].count -= read_wr.num_sge; - ch_sge_ary[ch_no].start += read_wr.num_sge; + if (read_wr.num_sge < chl_map->ch[ch_no].count) { + chl_map->ch[ch_no].count -= read_wr.num_sge; + chl_map->ch[ch_no].start += read_wr.num_sge; goto next_sge; } sgl_offset = 0; - err = 0; + err = 1; } out: - svc_rdma_put_context(tmp_sge_ctxt, 0); - svc_rdma_put_context(tmp_ch_ctxt, 0); + svc_rdma_put_req_map(rpl_map); + svc_rdma_put_req_map(chl_map); /* Detach arg pages. svc_recv will replenish them */ for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++) @@ -389,25 +376,12 @@ next_sge: while (rqstp->rq_resused) rqstp->rq_respages[--rqstp->rq_resused] = NULL; - if (err) { - printk(KERN_ERR "svcrdma : RDMA_READ error = %d\n", err); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - /* Free the linked list of read contexts */ - while (head != NULL) { - ctxt = head->next; - svc_rdma_put_context(head, 1); - head = ctxt; - } - return 0; - } - - return 1; + return err; } static int rdma_read_complete(struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *data) + struct svc_rdma_op_ctxt *head) { - struct svc_rdma_op_ctxt *head = data->next; int page_no; int ret; @@ -419,7 +393,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_pages[page_no] = head->pages[page_no]; } /* Point rq_arg.pages past header */ - rqstp->rq_arg.pages = &rqstp->rq_pages[head->sge[0].length]; + rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count]; rqstp->rq_arg.page_len = head->arg.page_len; rqstp->rq_arg.page_base = head->arg.page_base; @@ -433,21 +407,12 @@ static int rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_arg.len = head->arg.len; rqstp->rq_arg.buflen = head->arg.buflen; + /* Free the context */ + svc_rdma_put_context(head, 0); + /* XXX: What should this be? */ rqstp->rq_prot = IPPROTO_MAX; - - /* - * Free the contexts we used to build the RDMA_READ. We have - * to be careful here because the context list uses the same - * next pointer used to chain the contexts associated with the - * RDMA_READ - */ - data->next = NULL; /* terminate circular list */ - do { - data = head->next; - svc_rdma_put_context(head, 0); - head = data; - } while (head != NULL); + svc_xprt_copy_addrs(rqstp, rqstp->rq_xprt); ret = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len @@ -457,8 +422,6 @@ static int rdma_read_complete(struct svc_rqst *rqstp, ret, rqstp->rq_arg.len, rqstp->rq_arg.head[0].iov_base, rqstp->rq_arg.head[0].iov_len); - /* Indicate that we've consumed an RQ credit */ - rqstp->rq_xprt_ctxt = rqstp->rq_xprt; svc_xprt_received(rqstp->rq_xprt); return ret; } @@ -480,13 +443,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) dprintk("svcrdma: rqstp=%p\n", rqstp); - /* - * The rq_xprt_ctxt indicates if we've consumed an RQ credit - * or not. It is used in the rdma xpo_release_rqst function to - * determine whether or not to return an RQ WQE to the RQ. - */ - rqstp->rq_xprt_ctxt = NULL; - spin_lock_bh(&rdma_xprt->sc_read_complete_lock); if (!list_empty(&rdma_xprt->sc_read_complete_q)) { ctxt = list_entry(rdma_xprt->sc_read_complete_q.next, @@ -537,21 +493,22 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) /* If the request is invalid, reply with an error */ if (len < 0) { if (len == -ENOSYS) - (void)svc_rdma_send_error(rdma_xprt, rmsgp, ERR_VERS); + svc_rdma_send_error(rdma_xprt, rmsgp, ERR_VERS); goto close_out; } - /* Read read-list data. If we would need to wait, defer - * it. Not that in this case, we don't return the RQ credit - * until after the read completes. - */ - if (rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt)) { + /* Read read-list data. */ + ret = rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt); + if (ret > 0) { + /* read-list posted, defer until data received from client. */ svc_xprt_received(xprt); return 0; } - - /* Indicate we've consumed an RQ credit */ - rqstp->rq_xprt_ctxt = rqstp->rq_xprt; + if (ret < 0) { + /* Post of read-list failed, free context. */ + svc_rdma_put_context(ctxt, 1); + return 0; + } ret = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len @@ -569,11 +526,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) return ret; close_out: - if (ctxt) { + if (ctxt) svc_rdma_put_context(ctxt, 1); - /* Indicate we've consumed an RQ credit */ - rqstp->rq_xprt_ctxt = rqstp->rq_xprt; - } dprintk("svcrdma: transport %p is closing\n", xprt); /* * Set the close bit and enqueue it. svc_recv will see the diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 981f190..a19b22b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -63,52 +63,44 @@ * SGE[2..sge_count-2] data from xdr->pages[] * SGE[sge_count-1] data from xdr->tail. * + * The max SGE we need is the length of the XDR / pagesize + one for + * head + one for tail + one for RPCRDMA header. Since RPCSVC_MAXPAGES + * reserves a page for both the request and the reply header, and this + * array is only concerned with the reply we are assured that we have + * on extra page for the RPCRMDA header. */ -static struct ib_sge *xdr_to_sge(struct svcxprt_rdma *xprt, - struct xdr_buf *xdr, - struct ib_sge *sge, - int *sge_count) +static void xdr_to_sge(struct svcxprt_rdma *xprt, + struct xdr_buf *xdr, + struct svc_rdma_req_map *vec) { - /* Max we need is the length of the XDR / pagesize + one for - * head + one for tail + one for RPCRDMA header - */ int sge_max = (xdr->len+PAGE_SIZE-1) / PAGE_SIZE + 3; int sge_no; - u32 byte_count = xdr->len; u32 sge_bytes; u32 page_bytes; - int page_off; + u32 page_off; int page_no; + BUG_ON(xdr->len != + (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)); + /* Skip the first sge, this is for the RPCRDMA header */ sge_no = 1; /* Head SGE */ - sge[sge_no].addr = ib_dma_map_single(xprt->sc_cm_id->device, - xdr->head[0].iov_base, - xdr->head[0].iov_len, - DMA_TO_DEVICE); - sge_bytes = min_t(u32, byte_count, xdr->head[0].iov_len); - byte_count -= sge_bytes; - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + vec->sge[sge_no].iov_base = xdr->head[0].iov_base; + vec->sge[sge_no].iov_len = xdr->head[0].iov_len; sge_no++; /* pages SGE */ page_no = 0; page_bytes = xdr->page_len; page_off = xdr->page_base; - while (byte_count && page_bytes) { - sge_bytes = min_t(u32, byte_count, (PAGE_SIZE-page_off)); - sge[sge_no].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - xdr->pages[page_no], page_off, - sge_bytes, DMA_TO_DEVICE); - sge_bytes = min(sge_bytes, page_bytes); - byte_count -= sge_bytes; + while (page_bytes) { + vec->sge[sge_no].iov_base = + page_address(xdr->pages[page_no]) + page_off; + sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off)); page_bytes -= sge_bytes; - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + vec->sge[sge_no].iov_len = sge_bytes; sge_no++; page_no++; @@ -116,36 +108,24 @@ static struct ib_sge *xdr_to_sge(struct svcxprt_rdma *xprt, } /* Tail SGE */ - if (byte_count && xdr->tail[0].iov_len) { - sge[sge_no].addr = - ib_dma_map_single(xprt->sc_cm_id->device, - xdr->tail[0].iov_base, - xdr->tail[0].iov_len, - DMA_TO_DEVICE); - sge_bytes = min_t(u32, byte_count, xdr->tail[0].iov_len); - byte_count -= sge_bytes; - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + if (xdr->tail[0].iov_len) { + vec->sge[sge_no].iov_base = xdr->tail[0].iov_base; + vec->sge[sge_no].iov_len = xdr->tail[0].iov_len; sge_no++; } BUG_ON(sge_no > sge_max); - BUG_ON(byte_count != 0); - - *sge_count = sge_no; - return sge; + vec->count = sge_no; } - /* Assumptions: * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE */ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, u32 rmr, u64 to, u32 xdr_off, int write_len, - struct ib_sge *xdr_sge, int sge_count) + struct svc_rdma_req_map *vec) { - struct svc_rdma_op_ctxt *tmp_sge_ctxt; struct ib_send_wr write_wr; struct ib_sge *sge; int xdr_sge_no; @@ -154,25 +134,23 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, int sge_off; int bc; struct svc_rdma_op_ctxt *ctxt; - int ret = 0; - BUG_ON(sge_count > RPCSVC_MAXPAGES); + BUG_ON(vec->count > RPCSVC_MAXPAGES); dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, " - "write_len=%d, xdr_sge=%p, sge_count=%d\n", + "write_len=%d, vec->sge=%p, vec->count=%lu\n", rmr, (unsigned long long)to, xdr_off, - write_len, xdr_sge, sge_count); + write_len, vec->sge, vec->count); ctxt = svc_rdma_get_context(xprt); - ctxt->count = 0; - tmp_sge_ctxt = svc_rdma_get_context(xprt); - sge = tmp_sge_ctxt->sge; + ctxt->direction = DMA_TO_DEVICE; + sge = ctxt->sge; /* Find the SGE associated with xdr_off */ - for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < sge_count; + for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < vec->count; xdr_sge_no++) { - if (xdr_sge[xdr_sge_no].length > bc) + if (vec->sge[xdr_sge_no].iov_len > bc) break; - bc -= xdr_sge[xdr_sge_no].length; + bc -= vec->sge[xdr_sge_no].iov_len; } sge_off = bc; @@ -180,21 +158,28 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, sge_no = 0; /* Copy the remaining SGE */ - while (bc != 0 && xdr_sge_no < sge_count) { - sge[sge_no].addr = xdr_sge[xdr_sge_no].addr + sge_off; - sge[sge_no].lkey = xdr_sge[xdr_sge_no].lkey; + while (bc != 0 && xdr_sge_no < vec->count) { + sge[sge_no].lkey = xprt->sc_phys_mr->lkey; sge_bytes = min((size_t)bc, - (size_t)(xdr_sge[xdr_sge_no].length-sge_off)); + (size_t)(vec->sge[xdr_sge_no].iov_len-sge_off)); sge[sge_no].length = sge_bytes; - + atomic_inc(&xprt->sc_dma_used); + sge[sge_no].addr = + ib_dma_map_single(xprt->sc_cm_id->device, + (void *) + vec->sge[xdr_sge_no].iov_base + sge_off, + sge_bytes, DMA_TO_DEVICE); + if (dma_mapping_error(sge[sge_no].addr)) + goto err; sge_off = 0; sge_no++; + ctxt->count++; xdr_sge_no++; bc -= sge_bytes; } BUG_ON(bc != 0); - BUG_ON(xdr_sge_no > sge_count); + BUG_ON(xdr_sge_no > vec->count); /* Prepare WRITE WR */ memset(&write_wr, 0, sizeof write_wr); @@ -209,21 +194,20 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, /* Post It */ atomic_inc(&rdma_stat_write); - if (svc_rdma_send(xprt, &write_wr)) { - svc_rdma_put_context(ctxt, 1); - /* Fatal error, close transport */ - ret = -EIO; - } - svc_rdma_put_context(tmp_sge_ctxt, 0); - return ret; + if (svc_rdma_send(xprt, &write_wr)) + goto err; + return 0; + err: + svc_rdma_put_context(ctxt, 0); + /* Fatal error, close transport */ + return -EIO; } static int send_write_chunks(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_argp, struct rpcrdma_msg *rdma_resp, struct svc_rqst *rqstp, - struct ib_sge *sge, - int sge_count) + struct svc_rdma_req_map *vec) { u32 xfer_len = rqstp->rq_res.page_len + rqstp->rq_res.tail[0].iov_len; int write_len; @@ -269,8 +253,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, rs_offset + chunk_off, xdr_off, this_write, - sge, - sge_count); + vec); if (ret) { dprintk("svcrdma: RDMA_WRITE failed, ret=%d\n", ret); @@ -292,8 +275,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_argp, struct rpcrdma_msg *rdma_resp, struct svc_rqst *rqstp, - struct ib_sge *sge, - int sge_count) + struct svc_rdma_req_map *vec) { u32 xfer_len = rqstp->rq_res.len; int write_len; @@ -341,8 +323,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, rs_offset + chunk_off, xdr_off, this_write, - sge, - sge_count); + vec); if (ret) { dprintk("svcrdma: RDMA_WRITE failed, ret=%d\n", ret); @@ -380,7 +361,7 @@ static int send_reply(struct svcxprt_rdma *rdma, struct page *page, struct rpcrdma_msg *rdma_resp, struct svc_rdma_op_ctxt *ctxt, - int sge_count, + struct svc_rdma_req_map *vec, int byte_count) { struct ib_send_wr send_wr; @@ -389,11 +370,23 @@ static int send_reply(struct svcxprt_rdma *rdma, int page_no; int ret; + /* Post a recv buffer to handle another request. */ + ret = svc_rdma_post_recv(rdma); + if (ret) { + printk(KERN_INFO + "svcrdma: could not post a receive buffer, err=%d." + "Closing transport %p.\n", ret, rdma); + set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); + svc_rdma_put_context(ctxt, 0); + return -ENOTCONN; + } + /* Prepare the context */ ctxt->pages[0] = page; ctxt->count = 1; /* Prepare the SGE for the RPCRDMA Header */ + atomic_inc(&rdma->sc_dma_used); ctxt->sge[0].addr = ib_dma_map_page(rdma->sc_cm_id->device, page, 0, PAGE_SIZE, DMA_TO_DEVICE); @@ -402,10 +395,16 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[0].lkey = rdma->sc_phys_mr->lkey; /* Determine how many of our SGE are to be transmitted */ - for (sge_no = 1; byte_count && sge_no < sge_count; sge_no++) { - sge_bytes = min((size_t)ctxt->sge[sge_no].length, - (size_t)byte_count); + for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) { + sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; + atomic_inc(&rdma->sc_dma_used); + ctxt->sge[sge_no].addr = + ib_dma_map_single(rdma->sc_cm_id->device, + vec->sge[sge_no].iov_base, + sge_bytes, DMA_TO_DEVICE); + ctxt->sge[sge_no].length = sge_bytes; + ctxt->sge[sge_no].lkey = rdma->sc_phys_mr->lkey; } BUG_ON(byte_count != 0); @@ -417,8 +416,10 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->pages[page_no+1] = rqstp->rq_respages[page_no]; ctxt->count++; rqstp->rq_respages[page_no] = NULL; + /* If there are more pages than SGE, terminate SGE list */ + if (page_no+1 >= sge_no) + ctxt->sge[page_no+1].length = 0; } - BUG_ON(sge_no > rdma->sc_max_sge); memset(&send_wr, 0, sizeof send_wr); ctxt->wr_op = IB_WR_SEND; @@ -462,20 +463,20 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) enum rpcrdma_proc reply_type; int ret; int inline_bytes; - struct ib_sge *sge; - int sge_count = 0; struct page *res_page; struct svc_rdma_op_ctxt *ctxt; + struct svc_rdma_req_map *vec; dprintk("svcrdma: sending response for rqstp=%p\n", rqstp); /* Get the RDMA request header. */ rdma_argp = xdr_start(&rqstp->rq_arg); - /* Build an SGE for the XDR */ + /* Build an req vec for the XDR */ ctxt = svc_rdma_get_context(rdma); ctxt->direction = DMA_TO_DEVICE; - sge = xdr_to_sge(rdma, &rqstp->rq_res, ctxt->sge, &sge_count); + vec = svc_rdma_get_req_map(); + xdr_to_sge(rdma, &rqstp->rq_res, vec); inline_bytes = rqstp->rq_res.len; @@ -492,7 +493,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) /* Send any write-chunk data and build resp write-list */ ret = send_write_chunks(rdma, rdma_argp, rdma_resp, - rqstp, sge, sge_count); + rqstp, vec); if (ret < 0) { printk(KERN_ERR "svcrdma: failed to send write chunks, rc=%d\n", ret); @@ -502,7 +503,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) /* Send any reply-list data and update resp reply-list */ ret = send_reply_chunks(rdma, rdma_argp, rdma_resp, - rqstp, sge, sge_count); + rqstp, vec); if (ret < 0) { printk(KERN_ERR "svcrdma: failed to send reply chunks, rc=%d\n", ret); @@ -510,11 +511,13 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) } inline_bytes -= ret; - ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, sge_count, + ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, vec, inline_bytes); + svc_rdma_put_req_map(vec); dprintk("svcrdma: send_reply returns %d\n", ret); return ret; error: + svc_rdma_put_req_map(vec); svc_rdma_put_context(ctxt, 0); put_page(res_page); return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index af408fc..19ddc38 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -84,67 +84,37 @@ struct svc_xprt_class svc_rdma_class = { .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, }; -static int rdma_bump_context_cache(struct svcxprt_rdma *xprt) +/* WR context cache. Created in svc_rdma.c */ +extern struct kmem_cache *svc_rdma_ctxt_cachep; + +struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { - int target; - int at_least_one = 0; struct svc_rdma_op_ctxt *ctxt; - target = min(xprt->sc_ctxt_cnt + xprt->sc_ctxt_bump, - xprt->sc_ctxt_max); - - spin_lock_bh(&xprt->sc_ctxt_lock); - while (xprt->sc_ctxt_cnt < target) { - xprt->sc_ctxt_cnt++; - spin_unlock_bh(&xprt->sc_ctxt_lock); - - ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL); - - spin_lock_bh(&xprt->sc_ctxt_lock); - if (ctxt) { - at_least_one = 1; - ctxt->next = xprt->sc_ctxt_head; - xprt->sc_ctxt_head = ctxt; - } else { - /* kmalloc failed...give up for now */ - xprt->sc_ctxt_cnt--; + while (1) { + ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, GFP_KERNEL); + if (ctxt) break; - } + schedule_timeout_uninterruptible(msecs_to_jiffies(500)); } - spin_unlock_bh(&xprt->sc_ctxt_lock); - dprintk("svcrdma: sc_ctxt_max=%d, sc_ctxt_cnt=%d\n", - xprt->sc_ctxt_max, xprt->sc_ctxt_cnt); - return at_least_one; + ctxt->xprt = xprt; + INIT_LIST_HEAD(&ctxt->dto_q); + ctxt->count = 0; + atomic_inc(&xprt->sc_ctxt_used); + return ctxt; } -struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) +static void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) { - struct svc_rdma_op_ctxt *ctxt; - - while (1) { - spin_lock_bh(&xprt->sc_ctxt_lock); - if (unlikely(xprt->sc_ctxt_head == NULL)) { - /* Try to bump my cache. */ - spin_unlock_bh(&xprt->sc_ctxt_lock); - - if (rdma_bump_context_cache(xprt)) - continue; - - printk(KERN_INFO "svcrdma: sleeping waiting for " - "context memory on xprt=%p\n", - xprt); - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - continue; - } - ctxt = xprt->sc_ctxt_head; - xprt->sc_ctxt_head = ctxt->next; - spin_unlock_bh(&xprt->sc_ctxt_lock); - ctxt->xprt = xprt; - INIT_LIST_HEAD(&ctxt->dto_q); - ctxt->count = 0; - break; + struct svcxprt_rdma *xprt = ctxt->xprt; + int i; + for (i = 0; i < ctxt->count && ctxt->sge[i].length; i++) { + atomic_dec(&xprt->sc_dma_used); + ib_dma_unmap_single(xprt->sc_cm_id->device, + ctxt->sge[i].addr, + ctxt->sge[i].length, + ctxt->direction); } - return ctxt; } void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) @@ -158,15 +128,34 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) for (i = 0; i < ctxt->count; i++) put_page(ctxt->pages[i]); - for (i = 0; i < ctxt->count; i++) - dma_unmap_single(xprt->sc_cm_id->device->dma_device, - ctxt->sge[i].addr, - ctxt->sge[i].length, - ctxt->direction); - spin_lock_bh(&xprt->sc_ctxt_lock); - ctxt->next = xprt->sc_ctxt_head; - xprt->sc_ctxt_head = ctxt; - spin_unlock_bh(&xprt->sc_ctxt_lock); + kmem_cache_free(svc_rdma_ctxt_cachep, ctxt); + atomic_dec(&xprt->sc_ctxt_used); +} + +/* Temporary NFS request map cache. Created in svc_rdma.c */ +extern struct kmem_cache *svc_rdma_map_cachep; + +/* + * Temporary NFS req mappings are shared across all transport + * instances. These are short lived and should be bounded by the number + * of concurrent server threads * depth of the SQ. + */ +struct svc_rdma_req_map *svc_rdma_get_req_map(void) +{ + struct svc_rdma_req_map *map; + while (1) { + map = kmem_cache_alloc(svc_rdma_map_cachep, GFP_KERNEL); + if (map) + break; + schedule_timeout_uninterruptible(msecs_to_jiffies(500)); + } + map->count = 0; + return map; +} + +void svc_rdma_put_req_map(struct svc_rdma_req_map *map) +{ + kmem_cache_free(svc_rdma_map_cachep, map); } /* ib_cq event handler */ @@ -228,23 +217,8 @@ static void dto_tasklet_func(unsigned long data) list_del_init(&xprt->sc_dto_q); spin_unlock_irqrestore(&dto_lock, flags); - if (test_and_clear_bit(RDMAXPRT_RQ_PENDING, &xprt->sc_flags)) { - ib_req_notify_cq(xprt->sc_rq_cq, IB_CQ_NEXT_COMP); - rq_cq_reap(xprt); - set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); - /* - * If data arrived before established event, - * don't enqueue. This defers RPC I/O until the - * RDMA connection is complete. - */ - if (!test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags)) - svc_xprt_enqueue(&xprt->sc_xprt); - } - - if (test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags)) { - ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP); - sq_cq_reap(xprt); - } + rq_cq_reap(xprt); + sq_cq_reap(xprt); svc_xprt_put(&xprt->sc_xprt); spin_lock_irqsave(&dto_lock, flags); @@ -263,11 +237,15 @@ static void rq_comp_handler(struct ib_cq *cq, void *cq_context) struct svcxprt_rdma *xprt = cq_context; unsigned long flags; + /* Guard against unconditional flush call for destroyed QP */ + if (atomic_read(&xprt->sc_xprt.xpt_ref.refcount)==0) + return; + /* * Set the bit regardless of whether or not it's on the list * because it may be on the list already due to an SQ * completion. - */ + */ set_bit(RDMAXPRT_RQ_PENDING, &xprt->sc_flags); /* @@ -290,6 +268,8 @@ static void rq_comp_handler(struct ib_cq *cq, void *cq_context) * * Take all completing WC off the CQE and enqueue the associated DTO * context on the dto_q for the transport. + * + * Note that caller must hold a transport reference. */ static void rq_cq_reap(struct svcxprt_rdma *xprt) { @@ -297,29 +277,48 @@ static void rq_cq_reap(struct svcxprt_rdma *xprt) struct ib_wc wc; struct svc_rdma_op_ctxt *ctxt = NULL; + if (!test_and_clear_bit(RDMAXPRT_RQ_PENDING, &xprt->sc_flags)) + return; + + ib_req_notify_cq(xprt->sc_rq_cq, IB_CQ_NEXT_COMP); atomic_inc(&rdma_stat_rq_poll); - spin_lock_bh(&xprt->sc_rq_dto_lock); while ((ret = ib_poll_cq(xprt->sc_rq_cq, 1, &wc)) > 0) { ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id; ctxt->wc_status = wc.status; ctxt->byte_len = wc.byte_len; + svc_rdma_unmap_dma(ctxt); if (wc.status != IB_WC_SUCCESS) { /* Close the transport */ + dprintk("svcrdma: transport closing putting ctxt %p\n", ctxt); set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); svc_rdma_put_context(ctxt, 1); + svc_xprt_put(&xprt->sc_xprt); continue; } + spin_lock_bh(&xprt->sc_rq_dto_lock); list_add_tail(&ctxt->dto_q, &xprt->sc_rq_dto_q); + spin_unlock_bh(&xprt->sc_rq_dto_lock); + svc_xprt_put(&xprt->sc_xprt); } - spin_unlock_bh(&xprt->sc_rq_dto_lock); if (ctxt) atomic_inc(&rdma_stat_rq_prod); + + set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); + /* + * If data arrived before established event, + * don't enqueue. This defers RPC I/O until the + * RDMA connection is complete. + */ + if (!test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags)) + svc_xprt_enqueue(&xprt->sc_xprt); } /* * Send Queue Completion Handler - potentially called on interrupt context. + * + * Note that caller must hold a transport reference. */ static void sq_cq_reap(struct svcxprt_rdma *xprt) { @@ -328,11 +327,17 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) struct ib_cq *cq = xprt->sc_sq_cq; int ret; + + if (!test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags)) + return; + + ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP); atomic_inc(&rdma_stat_sq_poll); while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) { ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id; xprt = ctxt->xprt; + svc_rdma_unmap_dma(ctxt); if (wc.status != IB_WC_SUCCESS) /* Close the transport */ set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); @@ -343,20 +348,25 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) switch (ctxt->wr_op) { case IB_WR_SEND: - case IB_WR_RDMA_WRITE: svc_rdma_put_context(ctxt, 1); break; + case IB_WR_RDMA_WRITE: + svc_rdma_put_context(ctxt, 0); + break; + case IB_WR_RDMA_READ: if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { + struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr; + BUG_ON(!read_hdr); set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); - set_bit(RDMACTXT_F_READ_DONE, &ctxt->flags); spin_lock_bh(&xprt->sc_read_complete_lock); - list_add_tail(&ctxt->dto_q, + list_add_tail(&read_hdr->dto_q, &xprt->sc_read_complete_q); spin_unlock_bh(&xprt->sc_read_complete_lock); svc_xprt_enqueue(&xprt->sc_xprt); } + svc_rdma_put_context(ctxt, 0); break; default: @@ -365,6 +375,7 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) wc.opcode, wc.status); break; } + svc_xprt_put(&xprt->sc_xprt); } if (ctxt) @@ -376,11 +387,15 @@ static void sq_comp_handler(struct ib_cq *cq, void *cq_context) struct svcxprt_rdma *xprt = cq_context; unsigned long flags; + /* Guard against unconditional flush call for destroyed QP */ + if (atomic_read(&xprt->sc_xprt.xpt_ref.refcount)==0) + return; + /* * Set the bit regardless of whether or not it's on the list * because it may be on the list already due to an RQ * completion. - */ + */ set_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags); /* @@ -398,39 +413,6 @@ static void sq_comp_handler(struct ib_cq *cq, void *cq_context) tasklet_schedule(&dto_tasklet); } -static void create_context_cache(struct svcxprt_rdma *xprt, - int ctxt_count, int ctxt_bump, int ctxt_max) -{ - struct svc_rdma_op_ctxt *ctxt; - int i; - - xprt->sc_ctxt_max = ctxt_max; - xprt->sc_ctxt_bump = ctxt_bump; - xprt->sc_ctxt_cnt = 0; - xprt->sc_ctxt_head = NULL; - for (i = 0; i < ctxt_count; i++) { - ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL); - if (ctxt) { - ctxt->next = xprt->sc_ctxt_head; - xprt->sc_ctxt_head = ctxt; - xprt->sc_ctxt_cnt++; - } - } -} - -static void destroy_context_cache(struct svc_rdma_op_ctxt *ctxt) -{ - struct svc_rdma_op_ctxt *next; - if (!ctxt) - return; - - do { - next = ctxt->next; - kfree(ctxt); - ctxt = next; - } while (next); -} - static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, int listener) { @@ -447,7 +429,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, spin_lock_init(&cma_xprt->sc_lock); spin_lock_init(&cma_xprt->sc_read_complete_lock); - spin_lock_init(&cma_xprt->sc_ctxt_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); cma_xprt->sc_ord = svcrdma_ord; @@ -456,21 +437,9 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, cma_xprt->sc_max_requests = svcrdma_max_requests; cma_xprt->sc_sq_depth = svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT; atomic_set(&cma_xprt->sc_sq_count, 0); + atomic_set(&cma_xprt->sc_ctxt_used, 0); - if (!listener) { - int reqs = cma_xprt->sc_max_requests; - create_context_cache(cma_xprt, - reqs << 1, /* starting size */ - reqs, /* bump amount */ - reqs + - cma_xprt->sc_sq_depth + - RPCRDMA_MAX_THREADS + 1); /* max */ - if (!cma_xprt->sc_ctxt_head) { - kfree(cma_xprt); - return NULL; - } - clear_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); - } else + if (listener) set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); return cma_xprt; @@ -506,6 +475,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) BUG_ON(sge_no >= xprt->sc_max_sge); page = svc_rdma_get_page(); ctxt->pages[sge_no] = page; + atomic_inc(&xprt->sc_dma_used); pa = ib_dma_map_page(xprt->sc_cm_id->device, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); @@ -520,7 +490,12 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) recv_wr.num_sge = ctxt->count; recv_wr.wr_id = (u64)(unsigned long)ctxt; + svc_xprt_get(&xprt->sc_xprt); ret = ib_post_recv(xprt->sc_qp, &recv_wr, &bad_recv_wr); + if (ret) { + svc_xprt_put(&xprt->sc_xprt); + svc_rdma_put_context(ctxt, 1); + } return ret; } @@ -535,10 +510,11 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) * will call the recvfrom method on the listen xprt which will accept the new * connection. */ -static void handle_connect_req(struct rdma_cm_id *new_cma_id) +static void handle_connect_req(struct rdma_cm_id *new_cma_id, size_t client_ird) { struct svcxprt_rdma *listen_xprt = new_cma_id->context; struct svcxprt_rdma *newxprt; + struct sockaddr *sa; /* Create a new transport */ newxprt = rdma_create_xprt(listen_xprt->sc_xprt.xpt_server, 0); @@ -551,6 +527,15 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id) dprintk("svcrdma: Creating newxprt=%p, cm_id=%p, listenxprt=%p\n", newxprt, newxprt->sc_cm_id, listen_xprt); + /* Save client advertised inbound read limit for use later in accept. */ + newxprt->sc_ord = client_ird; + + /* Set the local and remote addresses in the transport */ + sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; + svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa)); + sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr; + svc_xprt_set_local(&newxprt->sc_xprt, sa, svc_addr_len(sa)); + /* * Enqueue the new transport on the accept queue of the listening * transport @@ -581,7 +566,8 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, case RDMA_CM_EVENT_CONNECT_REQUEST: dprintk("svcrdma: Connect request on cma_id=%p, xprt = %p, " "event=%d\n", cma_id, cma_id->context, event->event); - handle_connect_req(cma_id); + handle_connect_req(cma_id, + event->param.conn.responder_resources); break; case RDMA_CM_EVENT_ESTABLISHED: @@ -627,6 +613,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, if (xprt) { set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + svc_xprt_put(xprt); } break; case RDMA_CM_EVENT_DEVICE_REMOVAL: @@ -661,31 +648,27 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, cma_xprt = rdma_create_xprt(serv, 1); if (!cma_xprt) - return ERR_PTR(ENOMEM); + return ERR_PTR(-ENOMEM); xprt = &cma_xprt->sc_xprt; listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP); if (IS_ERR(listen_id)) { - svc_xprt_put(&cma_xprt->sc_xprt); - dprintk("svcrdma: rdma_create_id failed = %ld\n", - PTR_ERR(listen_id)); - return (void *)listen_id; + ret = PTR_ERR(listen_id); + dprintk("svcrdma: rdma_create_id failed = %d\n", ret); + goto err0; } + ret = rdma_bind_addr(listen_id, sa); if (ret) { - rdma_destroy_id(listen_id); - svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret); - return ERR_PTR(ret); + goto err1; } cma_xprt->sc_cm_id = listen_id; ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG); if (ret) { - rdma_destroy_id(listen_id); - svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_listen failed = %d\n", ret); - return ERR_PTR(ret); + goto err1; } /* @@ -696,6 +679,12 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, svc_xprt_set_local(&cma_xprt->sc_xprt, sa, salen); return &cma_xprt->sc_xprt; + + err1: + rdma_destroy_id(listen_id); + err0: + kfree(cma_xprt); + return ERR_PTR(ret); } /* @@ -716,7 +705,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) struct rdma_conn_param conn_param; struct ib_qp_init_attr qp_attr; struct ib_device_attr devattr; - struct sockaddr *sa; int ret; int i; @@ -753,8 +741,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) (size_t)svcrdma_max_requests); newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests; - newxprt->sc_ord = min((size_t)devattr.max_qp_rd_atom, - (size_t)svcrdma_ord); + /* + * Limit ORD based on client limit, local device limit, and + * configured svcrdma limit. + */ + newxprt->sc_ord = min_t(size_t, devattr.max_qp_rd_atom, newxprt->sc_ord); + newxprt->sc_ord = min_t(size_t, svcrdma_ord, newxprt->sc_ord); newxprt->sc_pd = ib_alloc_pd(newxprt->sc_cm_id->device); if (IS_ERR(newxprt->sc_pd)) { @@ -826,7 +818,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) newxprt->sc_sq_depth = qp_attr.cap.max_send_wr; newxprt->sc_max_requests = qp_attr.cap.max_recv_wr; } - svc_xprt_get(&newxprt->sc_xprt); newxprt->sc_qp = newxprt->sc_cm_id->qp; /* Register all of physical memory */ @@ -850,6 +841,13 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Swap out the handler */ newxprt->sc_cm_id->event_handler = rdma_cma_handler; + /* + * Arm the CQs for the SQ and RQ before accepting so we can't + * miss the first message + */ + ib_req_notify_cq(newxprt->sc_sq_cq, IB_CQ_NEXT_COMP); + ib_req_notify_cq(newxprt->sc_rq_cq, IB_CQ_NEXT_COMP); + /* Accept Connection */ set_bit(RDMAXPRT_CONN_PENDING, &newxprt->sc_flags); memset(&conn_param, 0, sizeof conn_param); @@ -886,58 +884,26 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) newxprt->sc_max_requests, newxprt->sc_ord); - /* Set the local and remote addresses in the transport */ - sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; - svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa)); - sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr; - svc_xprt_set_local(&newxprt->sc_xprt, sa, svc_addr_len(sa)); - - ib_req_notify_cq(newxprt->sc_sq_cq, IB_CQ_NEXT_COMP); - ib_req_notify_cq(newxprt->sc_rq_cq, IB_CQ_NEXT_COMP); return &newxprt->sc_xprt; errout: dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret); /* Take a reference in case the DTO handler runs */ svc_xprt_get(&newxprt->sc_xprt); - if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) { + if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) ib_destroy_qp(newxprt->sc_qp); - svc_xprt_put(&newxprt->sc_xprt); - } rdma_destroy_id(newxprt->sc_cm_id); /* This call to put will destroy the transport */ svc_xprt_put(&newxprt->sc_xprt); return NULL; } -/* - * Post an RQ WQE to the RQ when the rqst is being released. This - * effectively returns an RQ credit to the client. The rq_xprt_ctxt - * will be null if the request is deferred due to an RDMA_READ or the - * transport had no data ready (EAGAIN). Note that an RPC deferred in - * svc_process will still return the credit, this is because the data - * is copied and no longer consume a WQE/WC. - */ static void svc_rdma_release_rqst(struct svc_rqst *rqstp) { - int err; - struct svcxprt_rdma *rdma = - container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt); - if (rqstp->rq_xprt_ctxt) { - BUG_ON(rqstp->rq_xprt_ctxt != rdma); - err = svc_rdma_post_recv(rdma); - if (err) - dprintk("svcrdma: failed to post an RQ WQE error=%d\n", - err); - } - rqstp->rq_xprt_ctxt = NULL; } /* - * When connected, an svc_xprt has at least three references: - * - * - A reference held by the QP. We still hold that here because this - * code deletes the QP and puts the reference. + * When connected, an svc_xprt has at least two references: * * - A reference held by the cm_id between the ESTABLISHED and * DISCONNECTED events. If the remote peer disconnected first, this @@ -946,7 +912,7 @@ static void svc_rdma_release_rqst(struct svc_rqst *rqstp) * - A reference held by the svc_recv code that called this function * as part of close processing. * - * At a minimum two references should still be held. + * At a minimum one references should still be held. */ static void svc_rdma_detach(struct svc_xprt *xprt) { @@ -956,23 +922,50 @@ static void svc_rdma_detach(struct svc_xprt *xprt) /* Disconnect and flush posted WQE */ rdma_disconnect(rdma->sc_cm_id); - - /* Destroy the QP if present (not a listener) */ - if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) { - ib_destroy_qp(rdma->sc_qp); - svc_xprt_put(xprt); - } - - /* Destroy the CM ID */ - rdma_destroy_id(rdma->sc_cm_id); } -static void svc_rdma_free(struct svc_xprt *xprt) +static void __svc_rdma_free(struct work_struct *work) { - struct svcxprt_rdma *rdma = (struct svcxprt_rdma *)xprt; + struct svcxprt_rdma *rdma = + container_of(work, struct svcxprt_rdma, sc_work); dprintk("svcrdma: svc_rdma_free(%p)\n", rdma); + /* We should only be called from kref_put */ - BUG_ON(atomic_read(&xprt->xpt_ref.refcount) != 0); + BUG_ON(atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0); + + /* + * Destroy queued, but not processed read completions. Note + * that this cleanup has to be done before destroying the + * cm_id because the device ptr is needed to unmap the dma in + * svc_rdma_put_context. + */ + while (!list_empty(&rdma->sc_read_complete_q)) { + struct svc_rdma_op_ctxt *ctxt; + ctxt = list_entry(rdma->sc_read_complete_q.next, + struct svc_rdma_op_ctxt, + dto_q); + list_del_init(&ctxt->dto_q); + svc_rdma_put_context(ctxt, 1); + } + + /* Destroy queued, but not processed recv completions */ + while (!list_empty(&rdma->sc_rq_dto_q)) { + struct svc_rdma_op_ctxt *ctxt; + ctxt = list_entry(rdma->sc_rq_dto_q.next, + struct svc_rdma_op_ctxt, + dto_q); + list_del_init(&ctxt->dto_q); + svc_rdma_put_context(ctxt, 1); + } + + /* Warn if we leaked a resource or under-referenced */ + WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0); + WARN_ON(atomic_read(&rdma->sc_dma_used) != 0); + + /* Destroy the QP if present (not a listener) */ + if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) + ib_destroy_qp(rdma->sc_qp); + if (rdma->sc_sq_cq && !IS_ERR(rdma->sc_sq_cq)) ib_destroy_cq(rdma->sc_sq_cq); @@ -985,10 +978,20 @@ static void svc_rdma_free(struct svc_xprt *xprt) if (rdma->sc_pd && !IS_ERR(rdma->sc_pd)) ib_dealloc_pd(rdma->sc_pd); - destroy_context_cache(rdma->sc_ctxt_head); + /* Destroy the CM ID */ + rdma_destroy_id(rdma->sc_cm_id); + kfree(rdma); } +static void svc_rdma_free(struct svc_xprt *xprt) +{ + struct svcxprt_rdma *rdma = + container_of(xprt, struct svcxprt_rdma, sc_xprt); + INIT_WORK(&rdma->sc_work, __svc_rdma_free); + schedule_work(&rdma->sc_work); +} + static int svc_rdma_has_wspace(struct svc_xprt *xprt) { struct svcxprt_rdma *rdma = @@ -1018,7 +1021,7 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) int ret; if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags)) - return 0; + return -ENOTCONN; BUG_ON(wr->send_flags != IB_SEND_SIGNALED); BUG_ON(((struct svc_rdma_op_ctxt *)(unsigned long)wr->wr_id)->wr_op != @@ -1029,7 +1032,8 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) if (xprt->sc_sq_depth == atomic_read(&xprt->sc_sq_count)) { spin_unlock_bh(&xprt->sc_lock); atomic_inc(&rdma_stat_sq_starve); - /* See if we can reap some SQ WR */ + + /* See if we can opportunistically reap SQ WR to make room */ sq_cq_reap(xprt); /* Wait until SQ WR available if SQ still full */ @@ -1041,22 +1045,25 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) continue; } /* Bumped used SQ WR count and post */ + svc_xprt_get(&xprt->sc_xprt); ret = ib_post_send(xprt->sc_qp, wr, &bad_wr); if (!ret) atomic_inc(&xprt->sc_sq_count); - else + else { + svc_xprt_put(&xprt->sc_xprt); dprintk("svcrdma: failed to post SQ WR rc=%d, " "sc_sq_count=%d, sc_sq_depth=%d\n", ret, atomic_read(&xprt->sc_sq_count), xprt->sc_sq_depth); + } spin_unlock_bh(&xprt->sc_lock); break; } return ret; } -int svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, - enum rpcrdma_errcode err) +void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, + enum rpcrdma_errcode err) { struct ib_send_wr err_wr; struct ib_sge sge; @@ -1073,6 +1080,7 @@ int svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, length = svc_rdma_xdr_encode_error(xprt, rmsgp, err, va); /* Prepare SGE for local address */ + atomic_inc(&xprt->sc_dma_used); sge.addr = ib_dma_map_page(xprt->sc_cm_id->device, p, 0, PAGE_SIZE, DMA_FROM_DEVICE); sge.lkey = xprt->sc_phys_mr->lkey; @@ -1094,9 +1102,8 @@ int svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, /* Post It */ ret = svc_rdma_send(xprt, &err_wr); if (ret) { - dprintk("svcrdma: Error posting send = %d\n", ret); + dprintk("svcrdma: Error %d posting send for protocol error\n", + ret); svc_rdma_put_context(ctxt, 1); } - - return ret; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e18cd36..657835f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -169,6 +169,11 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return (unix_peer(osk) == NULL || unix_our_peer(sk, osk)); } +static inline int unix_recvq_full(struct sock const *sk) +{ + return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; +} + static struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -482,6 +487,8 @@ static int unix_socketpair(struct socket *, struct socket *); static int unix_accept(struct socket *, struct socket *, int); static int unix_getname(struct socket *, struct sockaddr *, int *, int); static unsigned int unix_poll(struct file *, struct socket *, poll_table *); +static unsigned int unix_datagram_poll(struct file *, struct socket *, + poll_table *); static int unix_ioctl(struct socket *, unsigned int, unsigned long); static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct kiocb *, struct socket *, @@ -527,7 +534,7 @@ static const struct proto_ops unix_dgram_ops = { .socketpair = unix_socketpair, .accept = sock_no_accept, .getname = unix_getname, - .poll = datagram_poll, + .poll = unix_datagram_poll, .ioctl = unix_ioctl, .listen = sock_no_listen, .shutdown = unix_shutdown, @@ -548,7 +555,7 @@ static const struct proto_ops unix_seqpacket_ops = { .socketpair = unix_socketpair, .accept = unix_accept, .getname = unix_getname, - .poll = datagram_poll, + .poll = unix_datagram_poll, .ioctl = unix_ioctl, .listen = unix_listen, .shutdown = unix_shutdown, @@ -983,8 +990,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - (skb_queue_len(&other->sk_receive_queue) > - other->sk_max_ack_backlog); + unix_recvq_full(other); unix_state_unlock(other); @@ -1058,8 +1064,7 @@ restart: if (other->sk_state != TCP_LISTEN) goto out_unlock; - if (skb_queue_len(&other->sk_receive_queue) > - other->sk_max_ack_backlog) { + if (unix_recvq_full(other)) { err = -EAGAIN; if (!timeo) goto out_unlock; @@ -1428,9 +1433,7 @@ restart: goto out_unlock; } - if (unix_peer(other) != sk && - (skb_queue_len(&other->sk_receive_queue) > - other->sk_max_ack_backlog)) { + if (unix_peer(other) != sk && unix_recvq_full(other)) { if (!timeo) { err = -EAGAIN; goto out_unlock; @@ -1991,6 +1994,64 @@ static unsigned int unix_poll(struct file * file, struct socket *sock, poll_tabl return mask; } +static unsigned int unix_datagram_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct sock *sk = sock->sk, *peer; + unsigned int mask; + + poll_wait(file, sk->sk_sleep, wait); + + peer = unix_peer_get(sk); + if (peer) { + if (peer != sk) { + /* + * Writability of a connected socket additionally + * depends on the state of the receive queue of the + * peer. + */ + poll_wait(file, &unix_sk(peer)->peer_wait, wait); + } else { + sock_put(peer); + peer = NULL; + } + } + + mask = 0; + + /* exceptional events? */ + if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + mask |= POLLERR; + if (sk->sk_shutdown & RCV_SHUTDOWN) + mask |= POLLRDHUP; + if (sk->sk_shutdown == SHUTDOWN_MASK) + mask |= POLLHUP; + + /* readable? */ + if (!skb_queue_empty(&sk->sk_receive_queue) || + (sk->sk_shutdown & RCV_SHUTDOWN)) + mask |= POLLIN | POLLRDNORM; + + /* Connection-based need to check for termination and startup */ + if (sk->sk_type == SOCK_SEQPACKET) { + if (sk->sk_state == TCP_CLOSE) + mask |= POLLHUP; + /* connection hasn't started yet? */ + if (sk->sk_state == TCP_SYN_SENT) + return mask; + } + + /* writable? */ + if (unix_writable(sk) && !(peer && unix_recvq_full(peer))) + mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + else + set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + + if (peer) + sock_put(peer); + + return mask; +} #ifdef CONFIG_PROC_FS static struct sock *first_unix_socket(int *i) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2bdd4dd..fb75f26 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -187,7 +187,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) @@ -273,7 +274,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *cb) @@ -928,7 +930,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_station(struct sk_buff *skb, @@ -1267,7 +1270,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_mpath(struct sk_buff *skb, diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index ac765dd..23a2cc0 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -200,8 +200,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, { - .name = "hmac(ripemd160)", - .compat = "ripemd160", + .name = "hmac(rmd160)", + .compat = "rmd160", .uinfo = { .auth = { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a1b0fbe..b976d9e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -50,19 +50,8 @@ static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) switch (type) { case XFRMA_ALG_AUTH: - if (!algp->alg_key_len && - strcmp(algp->alg_name, "digest_null") != 0) - return -EINVAL; - break; - case XFRMA_ALG_CRYPT: - if (!algp->alg_key_len && - strcmp(algp->alg_name, "cipher_null") != 0) - return -EINVAL; - break; - case XFRMA_ALG_COMP: - /* Zero length keys are legal. */ break; default: |