diff options
author | Trond Myklebust <trond.myklebust@primarydata.com> | 2015-04-23 15:16:37 -0400 |
---|---|---|
committer | Trond Myklebust <trond.myklebust@primarydata.com> | 2015-04-23 15:16:37 -0400 |
commit | f139b6c676c7e49b66016b28bf3f8ec5c54be891 (patch) | |
tree | 742f00e431dded1daf642b44f4c199b318f255dc /net | |
parent | 21330b667070fd64b2340d8d31c1b0800df78ec8 (diff) | |
parent | d654788e98f74f2df8dfc6079fa314938f739486 (diff) | |
download | linux-f139b6c676c7e49b66016b28bf3f8ec5c54be891.tar.gz linux-f139b6c676c7e49b66016b28bf3f8ec5c54be891.tar.bz2 linux-f139b6c676c7e49b66016b28bf3f8ec5c54be891.zip |
Merge tag 'nfs-rdma-for-4.1-1' of git://git.linux-nfs.org/projects/anna/nfs-rdma
NFS: NFSoRDMA Client Changes
This patch series creates an operation vector for each of the different
memory registration modes. This should make it easier to one day increase
credit limit, rsize, and wsize.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Diffstat (limited to 'net')
60 files changed, 1294 insertions, 914 deletions
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index d8e376a5f0f1..36a1a739ad68 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -658,14 +658,30 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) static void p9_virtio_remove(struct virtio_device *vdev) { struct virtio_chan *chan = vdev->priv; - - if (chan->inuse) - p9_virtio_close(chan->client); - vdev->config->del_vqs(vdev); + unsigned long warning_time; mutex_lock(&virtio_9p_lock); + + /* Remove self from list so we don't get new users. */ list_del(&chan->chan_list); + warning_time = jiffies; + + /* Wait for existing users to close. */ + while (chan->inuse) { + mutex_unlock(&virtio_9p_lock); + msleep(250); + if (time_after(jiffies, warning_time + 10 * HZ)) { + dev_emerg(&vdev->dev, + "p9_virtio_remove: waiting for device in use.\n"); + warning_time = jiffies; + } + mutex_lock(&virtio_9p_lock); + } + mutex_unlock(&virtio_9p_lock); + + vdev->config->del_vqs(vdev); + sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); kfree(chan->tag); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index b087d278c679..1849d96b3c91 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -563,6 +563,8 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) */ del_nbp(p); + dev_set_mtu(br->dev, br_min_mtu(br)); + spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 769b185fefbd..a6e2da0bc718 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -281,7 +281,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, int copylen; ret = -EOPNOTSUPP; - if (m->msg_flags&MSG_OOB) + if (flags & MSG_OOB) goto read_error; skb = skb_recv_datagram(sk, flags, 0 , &ret); diff --git a/net/can/af_can.c b/net/can/af_can.c index 66e08040ced7..32d710eaf1fc 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -259,6 +259,9 @@ int can_send(struct sk_buff *skb, int loop) goto inval_skb; } + skb->ip_summed = CHECKSUM_UNNECESSARY; + + skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); diff --git a/net/compat.c b/net/compat.c index 94d3d5e97883..f7bd286a8280 100644 --- a/net/compat.c +++ b/net/compat.c @@ -49,6 +49,13 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg, __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + + if (!uaddr) + kmsg->msg_namelen = 0; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_control = compat_ptr(tmp3); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 25b4b5d23485..ee0608bb3bc0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2166,28 +2166,28 @@ replay: } } err = rtnl_configure_link(dev, ifm); - if (err < 0) { - if (ops->newlink) { - LIST_HEAD(list_kill); - - ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); - } else { - unregister_netdevice(dev); - } - goto out; - } - + if (err < 0) + goto out_unregister; if (link_net) { err = dev_change_net_namespace(dev, dest_net, ifname); if (err < 0) - unregister_netdevice(dev); + goto out_unregister; } out: if (link_net) put_net(link_net); put_net(dest_net); return err; +out_unregister: + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } + goto out; } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f80507823531..8e4ac97c8477 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3733,9 +3733,13 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, struct sock *sk, int tstype) { struct sk_buff *skb; - bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; + bool tsonly; - if (!sk || !skb_may_tx_timestamp(sk, tsonly)) + if (!sk) + return; + + tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; + if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) @@ -4173,7 +4177,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->ignore_df = 0; skb_dst_drop(skb); skb->mark = 0; - skb->sender_cpu = 0; + skb_sender_cpu_clear(skb); skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); diff --git a/net/core/sock.c b/net/core/sock.c index 93c8b20c91e4..78e89eb7eb70 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1655,6 +1655,10 @@ void sock_rfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_rfree); +/* + * Buffer destructor for skbs that are not used directly in read or write + * path, e.g. for error handler skbs. Automatically called from kfree_skb. + */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 433424804284..8ce351ffceb1 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -25,6 +25,8 @@ static int zero = 0; static int one = 1; static int ushort_max = USHRT_MAX; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -237,7 +239,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_max", @@ -245,7 +247,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", @@ -253,7 +255,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_default", @@ -261,7 +263,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "dev_weight", diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 14d02ea905b6..3e44b9b0b78e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -268,6 +268,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) timeo = schedule_timeout(timeo); + sched_annotate_sleep(); lock_sock(sk); err = 0; if (!reqsk_queue_empty(&icsk->icsk_accept_queue)) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 81751f12645f..592aff37366b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler( mutex_unlock(&inet_diag_table_mutex); } +static size_t inet_sk_attr_size(void) +{ + return nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, @@ -326,9 +340,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s if (err) goto out; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64, GFP_KERNEL); + rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 787b3c294ce6..d9bc28ac5d1b 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -67,6 +67,7 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + skb_sender_cpu_clear(skb); return dst_output(skb); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 2c8d98e728c0..145a50c4d566 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -659,27 +659,30 @@ EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) { struct iphdr iph; + int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; - if (skb_copy_bits(skb, 0, &iph, sizeof(iph)) < 0) + netoff = skb_network_offset(skb); + + if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); - if (skb->len < len || len < (iph.ihl * 4)) + if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, iph.ihl*4)) + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) return skb; - if (pskb_trim_rcsum(skb, len)) + if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 31d8c71986b4..5cd99271d3a6 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -432,17 +432,32 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf kfree_skb(skb); } -static bool ipv4_pktinfo_prepare_errqueue(const struct sock *sk, - const struct sk_buff *skb, - int ee_origin) +/* IPv4 supports cmsg on all imcp errors and some timestamps + * + * Timestamp code paths do not initialize the fields expected by cmsg: + * the PKTINFO fields in skb->cb[]. Fill those in here. + */ +static bool ipv4_datagram_support_cmsg(const struct sock *sk, + struct sk_buff *skb, + int ee_origin) { - struct in_pktinfo *info = PKTINFO_SKB_CB(skb); + struct in_pktinfo *info; + + if (ee_origin == SO_EE_ORIGIN_ICMP) + return true; - if ((ee_origin != SO_EE_ORIGIN_TIMESTAMPING) || - (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) || + if (ee_origin == SO_EE_ORIGIN_LOCAL) + return false; + + /* Support IP_PKTINFO on tstamp packets if requested, to correlate + * timestamp with egress dev. Not possible for packets without dev + * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). + */ + if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) || (!skb->dev)) return false; + info = PKTINFO_SKB_CB(skb); info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr; info->ipi_ifindex = skb->dev->ifindex; return true; @@ -483,7 +498,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr = SKB_EXT_ERR(skb); - if (sin && skb->len) { + if (sin && serr->port) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); @@ -496,9 +511,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); - if (skb->len && - (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || - ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin))) { + if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; if (inet_sk(sk)->cmsg_flags) diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 99e810f84671..cf5e82f39d3b 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -272,9 +272,9 @@ static void trace_packet(const struct sk_buff *skb, &chainname, &comment, &rulenum) != 0) break; - nf_log_packet(net, AF_INET, hook, skb, in, out, &trace_loginfo, - "TRACE: %s:%s:%s:%u ", - tablename, chainname, comment, rulenum); + nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); } #endif diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index e9f66e1cda50..208d5439e59b 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -259,6 +259,9 @@ int ping_init_sock(struct sock *sk) kgid_t low, high; int ret = 0; + if (sk->sk_family == AF_INET6) + sk->sk_ipv6only = 1; + inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; @@ -305,6 +308,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, if (addr_len < sizeof(*addr)) return -EINVAL; + if (addr->sin_family != AF_INET && + !(addr->sin_family == AF_UNSPEC && + addr->sin_addr.s_addr == htonl(INADDR_ANY))) + return -EAFNOSUPPORT; + pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); @@ -330,7 +338,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -EINVAL; if (addr->sin6_family != AF_INET6) - return -EINVAL; + return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); @@ -716,7 +724,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) - return -EINVAL; + return -EAFNOSUPPORT; daddr = usin->sin_addr.s_addr; /* no remote port */ } else { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9d72a0fcd928..995a2259bcfc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -835,17 +835,13 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); - u32 new_size_goal, size_goal, hlen; + u32 new_size_goal, size_goal; if (!large_allowed || !sk_can_gso(sk)) return mss_now; - /* Maybe we should/could use sk->sk_prot->max_header here ? */ - hlen = inet_csk(sk)->icsk_af_ops->net_header_len + - inet_csk(sk)->icsk_ext_hdr_len + - tp->tcp_header_len; - - new_size_goal = sk->sk_gso_max_size - 1 - hlen; + /* Note : tcp_tso_autosize() will eventually split this later */ + new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER; new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal); /* We try hard to avoid divides here */ diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index d694088214cd..62856e185a93 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -378,6 +378,12 @@ EXPORT_SYMBOL_GPL(tcp_slow_start); */ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { + /* If credits accumulated at a higher w, apply them gently now. */ + if (tp->snd_cwnd_cnt >= w) { + tp->snd_cwnd_cnt = 0; + tp->snd_cwnd++; + } + tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { u32 delta = tp->snd_cwnd_cnt / w; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 4b276d1ed980..06d3d665a9fd 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -306,8 +306,10 @@ tcp_friendliness: } } - if (ca->cnt == 0) /* cannot be zero */ - ca->cnt = 1; + /* The maximum rate of cwnd increase CUBIC allows is 1 packet per + * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. + */ + ca->cnt = max(ca->cnt, 2U); } static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a2a796c5536b..1db253e36045 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2773,15 +2773,11 @@ void tcp_send_fin(struct sock *sk) } else { /* Socket is locked, keep trying until memory is available. */ for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); if (skb) break; yield(); } - - /* Reserve space for headers and prepare control bits. */ - skb_reserve(skb, MAX_TCP_HEADER); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d5f6bd9a210a..dab73813cb92 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -63,6 +63,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) return err; IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; + skb->protocol = htons(ETH_P_IP); return x->outer_mode->output2(x, skb); } @@ -71,7 +72,6 @@ EXPORT_SYMBOL(xfrm4_prepare_output); int xfrm4_output_finish(struct sk_buff *skb) { memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - skb->protocol = htons(ETH_P_IP); #ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c215be70cac0..ace8daca5c83 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -325,14 +325,34 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) kfree_skb(skb); } -static void ip6_datagram_prepare_pktinfo_errqueue(struct sk_buff *skb) +/* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL. + * + * At one point, excluding local errors was a quick test to identify icmp/icmp6 + * errors. This is no longer true, but the test remained, so the v6 stack, + * unlike v4, also honors cmsg requests on all wifi and timestamp errors. + * + * Timestamp code paths do not initialize the fields expected by cmsg: + * the PKTINFO fields in skb->cb[]. Fill those in here. + */ +static bool ip6_datagram_support_cmsg(struct sk_buff *skb, + struct sock_exterr_skb *serr) { - int ifindex = skb->dev ? skb->dev->ifindex : -1; + if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || + serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) + return true; + + if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) + return false; + + if (!skb->dev) + return false; if (skb->protocol == htons(ETH_P_IPV6)) - IP6CB(skb)->iif = ifindex; + IP6CB(skb)->iif = skb->dev->ifindex; else - PKTINFO_SKB_CB(skb)->ipi_ifindex = ifindex; + PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex; + + return true; } /* @@ -369,7 +389,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr = SKB_EXT_ERR(skb); - if (sin && skb->len) { + if (sin && serr->port) { const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; @@ -394,14 +414,11 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); - if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL && skb->len) { + + if (ip6_datagram_support_cmsg(skb, serr)) { sin->sin6_family = AF_INET6; - if (np->rxopt.all) { - if (serr->ee.ee_origin != SO_EE_ORIGIN_ICMP && - serr->ee.ee_origin != SO_EE_ORIGIN_ICMP6) - ip6_datagram_prepare_pktinfo_errqueue(skb); + if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); - } if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b4d5e1d97c1b..27ca79682efb 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto again; flp6->saddr = saddr; } + err = rt->dst.error; goto out; } again: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0a04a37305d5..7e80b61b51ff 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -318,6 +318,7 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) static inline int ip6_forward_finish(struct sk_buff *skb) { + skb_sender_cpu_clear(skb); return dst_output(skb); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 266a264ec212..ddd94eca19b3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -314,7 +314,7 @@ out: * Create tunnel matching given parameters. * * Return: - * created tunnel or NULL + * created tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) @@ -322,7 +322,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; - int err; + int err = -ENOMEM; if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); @@ -348,7 +348,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) failed_free: ip6_dev_free(dev); failed: - return NULL; + return ERR_PTR(err); } /** @@ -362,7 +362,7 @@ failed: * tunnel device is created and registered for use. * * Return: - * matching tunnel or NULL + * matching tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, @@ -380,13 +380,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net, if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) { if (create) - return NULL; + return ERR_PTR(-EEXIST); return t; } } if (!create) - return NULL; + return ERR_PTR(-ENODEV); return ip6_tnl_create(net, p); } @@ -1420,7 +1420,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); - if (t == NULL) + if (IS_ERR(t)) t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); @@ -1445,7 +1445,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (!IS_ERR(t)) { if (t->dev != dev) { err = -EEXIST; break; @@ -1457,14 +1457,15 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) else err = ip6_tnl_update(t, &p1); } - if (t) { + if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + } else { + err = PTR_ERR(t); + } break; case SIOCDELTUNNEL: err = -EPERM; @@ -1478,7 +1479,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); - if (t == NULL) + if (IS_ERR(t)) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) @@ -1672,12 +1673,13 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net *net = dev_net(dev); - struct ip6_tnl *nt; + struct ip6_tnl *nt, *t; nt = netdev_priv(dev); ip6_tnl_netlink_parms(data, &nt->parms); - if (ip6_tnl_locate(net, &nt->parms, 0)) + t = ip6_tnl_locate(net, &nt->parms, 0); + if (!IS_ERR(t)) return -EEXIST; return ip6_tnl_create2(dev); @@ -1697,8 +1699,7 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], ip6_tnl_netlink_parms(data, &p); t = ip6_tnl_locate(net, &p, 0); - - if (t) { + if (!IS_ERR(t)) { if (t->dev != dev) return -EEXIST; } else diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e080fbbbc0e5..bb00c6f2a885 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -298,9 +298,9 @@ static void trace_packet(const struct sk_buff *skb, &chainname, &comment, &rulenum) != 0) break; - nf_log_packet(net, AF_INET6, hook, skb, in, out, &trace_loginfo, - "TRACE: %s:%s:%s:%u ", - tablename, chainname, comment, rulenum); + nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); } #endif diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index bd46f736f61d..a2dfff6ff227 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -102,9 +102,10 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); - if (msg->msg_namelen < sizeof(struct sockaddr_in6) || - u->sin6_family != AF_INET6) { + if (msg->msg_namelen < sizeof(*u)) return -EINVAL; + if (u->sin6_family != AF_INET6) { + return -EAFNOSUPPORT; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != u->sin6_scope_id) { diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ab889bb16b3c..be2c0ba82c85 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -112,11 +112,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - if (skb_shinfo(skb)->ip6_frag_id) - fptr->identification = skb_shinfo(skb)->ip6_frag_id; - else - ipv6_select_ident(fptr, - (struct rt6_info *)skb_dst(skb)); + if (!skb_shinfo(skb)->ip6_frag_id) + ipv6_proxy_select_ident(skb); + fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index ca3f29b98ae5..010f8bd2d577 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -114,6 +114,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) return err; skb->ignore_df = 1; + skb->protocol = htons(ETH_P_IPV6); return x->outer_mode->output2(x, skb); } @@ -122,7 +123,6 @@ EXPORT_SYMBOL(xfrm6_prepare_output); int xfrm6_output_finish(struct sk_buff *skb) { memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - skb->protocol = htons(ETH_P_IPV6); #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 48bf5a06847b..8d2d01b4800a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -200,6 +200,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: + offset += ipv6_optlen(exthdr); if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { struct ip6_mh *mh; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3afe36824703..8d53d65bd2ab 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -58,13 +58,24 @@ struct ieee80211_local; #define IEEE80211_UNSET_POWER_LEVEL INT_MIN /* - * Some APs experience problems when working with U-APSD. Decrease the - * probability of that happening by using legacy mode for all ACs but VO. - * The AP that caused us trouble was a Cisco 4410N. It ignores our - * setting, and always treats non-VO ACs as legacy. + * Some APs experience problems when working with U-APSD. Decreasing the + * probability of that happening by using legacy mode for all ACs but VO isn't + * enough. + * + * Cisco 4410N originally forced us to enable VO by default only because it + * treated non-VO ACs as legacy. + * + * However some APs (notably Netgear R7000) silently reclassify packets to + * different ACs. Since u-APSD ACs require trigger frames for frame retrieval + * clients would never see some frames (e.g. ARP responses) or would fetch them + * accidentally after a long time. + * + * It makes little sense to enable u-APSD queues by default because it needs + * userspace applications to be aware of it to actually take advantage of the + * possible additional powersavings. Implicitly depending on driver autotrigger + * frame support doesn't make much sense. */ -#define IEEE80211_DEFAULT_UAPSD_QUEUES \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VO +#define IEEE80211_DEFAULT_UAPSD_QUEUES 0 #define IEEE80211_DEFAULT_MAX_SP_LEN \ IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL @@ -453,6 +464,7 @@ struct ieee80211_if_managed { unsigned int flags; bool csa_waiting_bcn; + bool csa_ignored_same_chan; bool beacon_crc_valid; u32 beacon_crc; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 10ac6324c1d0..142f66aece18 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1150,6 +1150,17 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; } + if (cfg80211_chandef_identical(&csa_ie.chandef, + &sdata->vif.bss_conf.chandef)) { + if (ifmgd->csa_ignored_same_chan) + return; + sdata_info(sdata, + "AP %pM tries to chanswitch to same channel, ignore\n", + ifmgd->associated->bssid); + ifmgd->csa_ignored_same_chan = true; + return; + } + mutex_lock(&local->mtx); mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(sdata->vif.chanctx_conf, @@ -1210,6 +1221,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata->vif.csa_active = true; sdata->csa_chandef = csa_ie.chandef; sdata->csa_block_tx = csa_ie.mode; + ifmgd->csa_ignored_same_chan = false; if (sdata->csa_block_tx) ieee80211_stop_vif_queues(local, sdata, @@ -2090,6 +2102,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; + ifmgd->csa_ignored_same_chan = false; if (sdata->csa_block_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); @@ -3204,7 +3217,8 @@ static const u64 care_about_ies = (1ULL << WLAN_EID_CHANNEL_SWITCH) | (1ULL << WLAN_EID_PWR_CONSTRAINT) | (1ULL << WLAN_EID_HT_CAPABILITY) | - (1ULL << WLAN_EID_HT_OPERATION); + (1ULL << WLAN_EID_HT_OPERATION) | + (1ULL << WLAN_EID_EXT_CHANSWITCH_ANN); static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1101563357ea..944bdc04e913 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2214,6 +2214,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + if (ieee80211_drop_unencrypted(rx, hdr->frame_control)) + return RX_DROP_MONITOR; + /* frame is in RMC, don't forward */ if (ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8428f4a95479..747bdcf72e92 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3178,7 +3178,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, wdev_iter = &sdata_iter->wdev; if (sdata_iter == sdata || - rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL || + !ieee80211_sdata_running(sdata_iter) || local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype)) continue; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index c47ffd7a0a70..d93ceeb3ef04 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -896,6 +896,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + kfree(param->pe_data); } if (opt) @@ -1169,6 +1171,7 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #endif + ip_vs_pe_put(param.pe); return 0; /* Error exit */ out: diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 0d8448f19dfe..675d12c69e32 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -212,6 +212,30 @@ void nf_log_packet(struct net *net, } EXPORT_SYMBOL(nf_log_packet); +void nf_log_trace(struct net *net, + u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, const char *fmt, ...) +{ + va_list args; + char prefix[NF_LOG_PREFIXLEN]; + const struct nf_logger *logger; + + rcu_read_lock(); + logger = rcu_dereference(net->nf.nf_loggers[pf]); + if (logger) { + va_start(args, fmt); + vsnprintf(prefix, sizeof(prefix), fmt, args); + va_end(args); + logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(nf_log_trace); + #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 199fd0f27b0e..ac1a9528dbf2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -227,7 +227,7 @@ nft_rule_deactivate_next(struct net *net, struct nft_rule *rule) static inline void nft_rule_clear(struct net *net, struct nft_rule *rule) { - rule->genmask = 0; + rule->genmask &= ~(1 << gencursor_next(net)); } static int @@ -1225,7 +1225,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_CHAIN_POLICY]) { if ((chain != NULL && - !(chain->flags & NFT_BASE_CHAIN)) || + !(chain->flags & NFT_BASE_CHAIN))) + return -EOPNOTSUPP; + + if (chain == NULL && nla[NFTA_CHAIN_HOOK] == NULL) return -EOPNOTSUPP; @@ -1711,9 +1714,12 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, } nla_nest_end(skb, list); - if (rule->ulen && - nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule))) - goto nla_put_failure; + if (rule->udata) { + struct nft_userdata *udata = nft_userdata(rule); + if (nla_put(skb, NFTA_RULE_USERDATA, udata->len + 1, + udata->data) < 0) + goto nla_put_failure; + } nlmsg_end(skb, nlh); return 0; @@ -1896,11 +1902,12 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule, *old_rule = NULL; + struct nft_userdata *udata; struct nft_trans *trans = NULL; struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; - unsigned int size, i, n, ulen = 0; + unsigned int size, i, n, ulen = 0, usize = 0; int err, rem; bool create; u64 handle, pos_handle; @@ -1968,12 +1975,19 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, n++; } } + /* Check for overflow of dlen field */ + err = -EFBIG; + if (size >= 1 << 12) + goto err1; - if (nla[NFTA_RULE_USERDATA]) + if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); + if (ulen > 0) + usize = sizeof(struct nft_userdata) + ulen; + } err = -ENOMEM; - rule = kzalloc(sizeof(*rule) + size + ulen, GFP_KERNEL); + rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL); if (rule == NULL) goto err1; @@ -1981,10 +1995,13 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, rule->handle = handle; rule->dlen = size; - rule->ulen = ulen; + rule->udata = ulen ? 1 : 0; - if (ulen) - nla_memcpy(nft_userdata(rule), nla[NFTA_RULE_USERDATA], ulen); + if (ulen) { + udata = nft_userdata(rule); + udata->len = ulen - 1; + nla_memcpy(udata->data, nla[NFTA_RULE_USERDATA], ulen); + } expr = nft_expr_first(rule); for (i = 0; i < n; i++) { @@ -2031,12 +2048,6 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, err3: list_del_rcu(&rule->list); - if (trans) { - list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_clear(net, nft_trans_rule(trans)); - nft_trans_destroy(trans); - chain->use++; - } err2: nf_tables_rule_destroy(&ctx, rule); err1: @@ -3612,12 +3623,11 @@ static int nf_tables_commit(struct sk_buff *skb) &te->elem, NFT_MSG_DELSETELEM, 0); te->set->ops->get(te->set, &te->elem); - te->set->ops->remove(te->set, &te->elem); nft_data_uninit(&te->elem.key, NFT_DATA_VALUE); - if (te->elem.flags & NFT_SET_MAP) { - nft_data_uninit(&te->elem.data, - te->set->dtype); - } + if (te->set->flags & NFT_SET_MAP && + !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END)) + nft_data_uninit(&te->elem.data, te->set->dtype); + te->set->ops->remove(te->set, &te->elem); nft_trans_destroy(trans); break; } @@ -3658,7 +3668,7 @@ static int nf_tables_abort(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); struct nft_trans *trans, *next; - struct nft_set *set; + struct nft_trans_elem *te; list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { switch (trans->msg_type) { @@ -3719,9 +3729,13 @@ static int nf_tables_abort(struct sk_buff *skb) break; case NFT_MSG_NEWSETELEM: nft_trans_elem_set(trans)->nelems--; - set = nft_trans_elem_set(trans); - set->ops->get(set, &nft_trans_elem(trans)); - set->ops->remove(set, &nft_trans_elem(trans)); + te = (struct nft_trans_elem *)trans->data; + te->set->ops->get(te->set, &te->elem); + nft_data_uninit(&te->elem.key, NFT_DATA_VALUE); + if (te->set->flags & NFT_SET_MAP && + !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END)) + nft_data_uninit(&te->elem.data, te->set->dtype); + te->set->ops->remove(te->set, &te->elem); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 3b90eb2b2c55..2d298dccb6dd 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -94,10 +94,10 @@ static void nft_trace_packet(const struct nft_pktinfo *pkt, { struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, - pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", - chain->table->name, chain->name, comments[type], - rulenum); + nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, + pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", + chain->table->name, chain->name, comments[type], + rulenum); } unsigned int diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index a5599fc51a6f..54330fb5efaf 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) return -EINVAL; + /* Not all fields are initialized so first zero the tuple */ + memset(tuple, 0, sizeof(struct nf_conntrack_tuple)); + tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM])); tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 1279cd85663e..65f3e2b6be44 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -123,7 +123,7 @@ static void nft_target_set_tgchk_param(struct xt_tgchk_param *par, const struct nft_ctx *ctx, struct xt_target *target, void *info, - union nft_entry *entry, u8 proto, bool inv) + union nft_entry *entry, u16 proto, bool inv) { par->net = ctx->net; par->table = ctx->table->name; @@ -133,11 +133,14 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; case NFPROTO_BRIDGE: - entry->ebt.ethproto = proto; + entry->ebt.ethproto = (__force __be16)proto; entry->ebt.invflags = inv ? EBT_IPROTO : 0; break; } @@ -171,7 +174,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] [NFTA_RULE_COMPAT_FLAGS] = { .type = NLA_U32 }, }; -static int nft_parse_compat(const struct nlattr *attr, u8 *proto, bool *inv) +static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; u32 flags; @@ -203,7 +206,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_target *target = expr->ops->data; struct xt_tgchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO])); - u8 proto = 0; + u16 proto = 0; bool inv = false; union nft_entry e = {}; int ret; @@ -334,7 +337,7 @@ static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { static void nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, struct xt_match *match, void *info, - union nft_entry *entry, u8 proto, bool inv) + union nft_entry *entry, u16 proto, bool inv) { par->net = ctx->net; par->table = ctx->table->name; @@ -344,11 +347,14 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; case NFPROTO_BRIDGE: - entry->ebt.ethproto = proto; + entry->ebt.ethproto = (__force __be16)proto; entry->ebt.invflags = inv ? EBT_IPROTO : 0; break; } @@ -385,7 +391,7 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_match *match = expr->ops->data; struct xt_mtchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO])); - u8 proto = 0; + u16 proto = 0; bool inv = false; union nft_entry e = {}; int ret; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index c82df0a48fcd..37c15e674884 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -153,6 +153,8 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, iter->err = err; goto out; } + + continue; } if (iter->count < iter->skip) diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index ef8a926752a9..50e1e5aaf4ce 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -513,8 +513,8 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_ip6 *i = par->entryinfo; - if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) - && !(i->flags & IP6T_INV_PROTO)) + if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) && + !(i->invflags & IP6T_INV_PROTO)) return 0; pr_info("Can be used only in combination with " diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5bf1e968a728..f8db7064d81c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3123,11 +3123,18 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, return 0; } -static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what) +static void packet_dev_mclist_delete(struct net_device *dev, + struct packet_mclist **mlp) { - for ( ; i; i = i->next) { - if (i->ifindex == dev->ifindex) - packet_dev_mc(dev, i, what); + struct packet_mclist *ml; + + while ((ml = *mlp) != NULL) { + if (ml->ifindex == dev->ifindex) { + packet_dev_mc(dev, ml, -1); + *mlp = ml->next; + kfree(ml); + } else + mlp = &ml->next; } } @@ -3204,12 +3211,11 @@ static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) packet_dev_mc(dev, ml, -1); kfree(ml); } - rtnl_unlock(); - return 0; + break; } } rtnl_unlock(); - return -EADDRNOTAVAIL; + return 0; } static void packet_flush_mclist(struct sock *sk) @@ -3559,7 +3565,7 @@ static int packet_notifier(struct notifier_block *this, switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) - packet_dev_mclist(dev, po->mclist, -1); + packet_dev_mclist_delete(dev, &po->mclist); /* fallthrough */ case NETDEV_DOWN: diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index a817705ce2d0..dba8d0864f18 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, int *unpinned); static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); -static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id) +static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst, + struct rds_iw_device **rds_iwdev, + struct rdma_cm_id **cm_id) { struct rds_iw_device *iwdev; struct rds_iw_cm_id *i_cm_id; @@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd src_addr->sin_port, dst_addr->sin_addr.s_addr, dst_addr->sin_port, - rs->rs_bound_addr, - rs->rs_bound_port, - rs->rs_conn_addr, - rs->rs_conn_port); + src->sin_addr.s_addr, + src->sin_port, + dst->sin_addr.s_addr, + dst->sin_port); #ifdef WORKING_TUPLE_DETECTION - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr && - src_addr->sin_port == rs->rs_bound_port && - dst_addr->sin_addr.s_addr == rs->rs_conn_addr && - dst_addr->sin_port == rs->rs_conn_port) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr && + src_addr->sin_port == src->sin_port && + dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr && + dst_addr->sin_port == dst->sin_port) { #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only @@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd * zero'ed. It doesn't appear to be properly populated * during connection setup... */ - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) { #endif spin_unlock_irq(&iwdev->spinlock); *rds_iwdev = iwdev; @@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i { struct sockaddr_in *src_addr, *dst_addr; struct rds_iw_device *rds_iwdev_old; - struct rds_sock rs; struct rdma_cm_id *pcm_id; int rc; src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr; dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr; - rs.rs_bound_addr = src_addr->sin_addr.s_addr; - rs.rs_bound_port = src_addr->sin_port; - rs.rs_conn_addr = dst_addr->sin_addr.s_addr; - rs.rs_conn_port = dst_addr->sin_port; - - rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id); + rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id); if (rc) rds_iw_remove_cm_id(rds_iwdev, cm_id); @@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_iw_device *rds_iwdev; struct rds_iw_mr *ibmr = NULL; struct rdma_cm_id *cm_id; + struct sockaddr_in src = { + .sin_addr.s_addr = rs->rs_bound_addr, + .sin_port = rs->rs_bound_port, + }; + struct sockaddr_in dst = { + .sin_addr.s_addr = rs->rs_conn_addr, + .sin_port = rs->rs_conn_port, + }; int ret; - ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id); + ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id); if (ret || !cm_id) { ret = -ENODEV; goto out; diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index 5394b6be46ec..0610efa83d72 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -42,7 +42,8 @@ void rxrpc_UDP_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } - if (!skb->len) { + serr = SKB_EXT_ERR(skb); + if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); kfree_skb(skb); return; @@ -50,7 +51,6 @@ void rxrpc_UDP_error_report(struct sock *sk) rxrpc_new_skb(skb); - serr = SKB_EXT_ERR(skb); addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); port = serr->port; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 4575485ad1b4..19a560626dc4 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) { /* nothing remains on the queue */ if (copied && - (msg->msg_flags & MSG_PEEK || timeo == 0)) + (flags & MSG_PEEK || timeo == 0)) goto out; /* wait for a message to turn up */ diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 82c5d7fc1988..5f6288fa3f12 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -25,21 +25,41 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_bpf *b = a->priv; - int action; - int filter_res; + int action, filter_res; spin_lock(&b->tcf_lock); + b->tcf_tm.lastuse = jiffies; bstats_update(&b->tcf_bstats, skb); - action = b->tcf_action; filter_res = BPF_PROG_RUN(b->filter, skb); - if (filter_res == 0) { - /* Return code 0 from the BPF program - * is being interpreted as a drop here. - */ - action = TC_ACT_SHOT; + + /* A BPF program may overwrite the default action opcode. + * Similarly as in cls_bpf, if filter_res == -1 we use the + * default action specified from tc. + * + * In case a different well-known TC_ACT opcode has been + * returned, it will overwrite the default one. + * + * For everything else that is unkown, TC_ACT_UNSPEC is + * returned. + */ + switch (filter_res) { + case TC_ACT_PIPE: + case TC_ACT_RECLASSIFY: + case TC_ACT_OK: + action = filter_res; + break; + case TC_ACT_SHOT: + action = filter_res; b->tcf_qstats.drops++; + break; + case TC_ACT_UNSPEC: + action = b->tcf_action; + break; + default: + action = TC_ACT_UNSPEC; + break; } spin_unlock(&b->tcf_lock); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 09487afbfd51..95fdf4e40051 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -78,8 +78,11 @@ struct tc_u_hnode { struct tc_u_common *tp_c; int refcnt; unsigned int divisor; - struct tc_u_knode __rcu *ht[1]; struct rcu_head rcu; + /* The 'ht' field MUST be the last field in structure to allow for + * more entries allocated at end of structure. + */ + struct tc_u_knode __rcu *ht[1]; }; struct tc_u_common { diff --git a/net/socket.c b/net/socket.c index bbedbfcb42c2..245330ca0015 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1702,6 +1702,8 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, if (len > INT_MAX) len = INT_MAX; + if (unlikely(!access_ok(VERIFY_READ, buff, len))) + return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1760,6 +1762,8 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, if (size > INT_MAX) size = INT_MAX; + if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size))) + return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index da5136fd5694..579f72bbcf4b 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,6 +1,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o -xprtrdma-y := transport.o rpc_rdma.o verbs.o +xprtrdma-y := transport.o rpc_rdma.o verbs.o \ + fmr_ops.o frwr_ops.o physical_ops.o obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c new file mode 100644 index 000000000000..a91ba2c8ef1e --- /dev/null +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -0,0 +1,208 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + */ + +/* Lightweight memory registration using Fast Memory Regions (FMR). + * Referred to sometimes as MTHCAFMR mode. + * + * FMR uses synchronous memory registration and deregistration. + * FMR registration is known to be fast, but FMR deregistration + * can take tens of usecs to complete. + */ + +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +/* Maximum scatter/gather per FMR */ +#define RPCRDMA_MAX_FMR_SGES (64) + +static int +fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) +{ + return 0; +} + +/* FMR mode conveys up to 64 pages of payload per chunk segment. + */ +static size_t +fmr_op_maxpages(struct rpcrdma_xprt *r_xprt) +{ + return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + rpcrdma_max_segments(r_xprt) * RPCRDMA_MAX_FMR_SGES); +} + +static int +fmr_op_init(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; + struct ib_fmr_attr fmr_attr = { + .max_pages = RPCRDMA_MAX_FMR_SGES, + .max_maps = 1, + .page_shift = PAGE_SHIFT + }; + struct ib_pd *pd = r_xprt->rx_ia.ri_pd; + struct rpcrdma_mw *r; + int i, rc; + + INIT_LIST_HEAD(&buf->rb_mws); + INIT_LIST_HEAD(&buf->rb_all); + + i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; + dprintk("RPC: %s: initalizing %d FMRs\n", __func__, i); + + while (i--) { + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return -ENOMEM; + + r->r.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr); + if (IS_ERR(r->r.fmr)) + goto out_fmr_err; + + list_add(&r->mw_list, &buf->rb_mws); + list_add(&r->mw_all, &buf->rb_all); + } + return 0; + +out_fmr_err: + rc = PTR_ERR(r->r.fmr); + dprintk("RPC: %s: ib_alloc_fmr status %i\n", __func__, rc); + kfree(r); + return rc; +} + +/* Use the ib_map_phys_fmr() verb to register a memory region + * for remote access via RDMA READ or RDMA WRITE. + */ +static int +fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int nsegs, bool writing) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct ib_device *device = ia->ri_id->device; + enum dma_data_direction direction = rpcrdma_data_dir(writing); + struct rpcrdma_mr_seg *seg1 = seg; + struct rpcrdma_mw *mw = seg1->rl_mw; + u64 physaddrs[RPCRDMA_MAX_DATA_SEGS]; + int len, pageoff, i, rc; + + pageoff = offset_in_page(seg1->mr_offset); + seg1->mr_offset -= pageoff; /* start of page */ + seg1->mr_len += pageoff; + len = -pageoff; + if (nsegs > RPCRDMA_MAX_FMR_SGES) + nsegs = RPCRDMA_MAX_FMR_SGES; + for (i = 0; i < nsegs;) { + rpcrdma_map_one(device, seg, direction); + physaddrs[i] = seg->mr_dma; + len += seg->mr_len; + ++seg; + ++i; + /* Check for holes */ + if ((i < nsegs && offset_in_page(seg->mr_offset)) || + offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) + break; + } + + rc = ib_map_phys_fmr(mw->r.fmr, physaddrs, i, seg1->mr_dma); + if (rc) + goto out_maperr; + + seg1->mr_rkey = mw->r.fmr->rkey; + seg1->mr_base = seg1->mr_dma + pageoff; + seg1->mr_nsegs = i; + seg1->mr_len = len; + return i; + +out_maperr: + dprintk("RPC: %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", + __func__, len, (unsigned long long)seg1->mr_dma, + pageoff, i, rc); + while (i--) + rpcrdma_unmap_one(device, --seg); + return rc; +} + +/* Use the ib_unmap_fmr() verb to prevent further remote + * access via RDMA READ or RDMA WRITE. + */ +static int +fmr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct rpcrdma_mr_seg *seg1 = seg; + struct ib_device *device; + int rc, nsegs = seg->mr_nsegs; + LIST_HEAD(l); + + list_add(&seg1->rl_mw->r.fmr->list, &l); + rc = ib_unmap_fmr(&l); + read_lock(&ia->ri_qplock); + device = ia->ri_id->device; + while (seg1->mr_nsegs--) + rpcrdma_unmap_one(device, seg++); + read_unlock(&ia->ri_qplock); + if (rc) + goto out_err; + return nsegs; + +out_err: + dprintk("RPC: %s: ib_unmap_fmr status %i\n", __func__, rc); + return nsegs; +} + +/* After a disconnect, unmap all FMRs. + * + * This is invoked only in the transport connect worker in order + * to serialize with rpcrdma_register_fmr_external(). + */ +static void +fmr_op_reset(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_mw *r; + LIST_HEAD(list); + int rc; + + list_for_each_entry(r, &buf->rb_all, mw_all) + list_add(&r->r.fmr->list, &list); + + rc = ib_unmap_fmr(&list); + if (rc) + dprintk("RPC: %s: ib_unmap_fmr failed %i\n", + __func__, rc); +} + +static void +fmr_op_destroy(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_mw *r; + int rc; + + while (!list_empty(&buf->rb_all)) { + r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); + list_del(&r->mw_all); + rc = ib_dealloc_fmr(r->r.fmr); + if (rc) + dprintk("RPC: %s: ib_dealloc_fmr failed %i\n", + __func__, rc); + kfree(r); + } +} + +const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { + .ro_map = fmr_op_map, + .ro_unmap = fmr_op_unmap, + .ro_open = fmr_op_open, + .ro_maxpages = fmr_op_maxpages, + .ro_init = fmr_op_init, + .ro_reset = fmr_op_reset, + .ro_destroy = fmr_op_destroy, + .ro_displayname = "fmr", +}; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c new file mode 100644 index 000000000000..0a7b9df70133 --- /dev/null +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -0,0 +1,353 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + */ + +/* Lightweight memory registration using Fast Registration Work + * Requests (FRWR). Also referred to sometimes as FRMR mode. + * + * FRWR features ordered asynchronous registration and deregistration + * of arbitrarily sized memory regions. This is the fastest and safest + * but most complex memory registration mode. + */ + +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +static int +__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, + unsigned int depth) +{ + struct rpcrdma_frmr *f = &r->r.frmr; + int rc; + + f->fr_mr = ib_alloc_fast_reg_mr(pd, depth); + if (IS_ERR(f->fr_mr)) + goto out_mr_err; + f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth); + if (IS_ERR(f->fr_pgl)) + goto out_list_err; + return 0; + +out_mr_err: + rc = PTR_ERR(f->fr_mr); + dprintk("RPC: %s: ib_alloc_fast_reg_mr status %i\n", + __func__, rc); + return rc; + +out_list_err: + rc = PTR_ERR(f->fr_pgl); + dprintk("RPC: %s: ib_alloc_fast_reg_page_list status %i\n", + __func__, rc); + ib_dereg_mr(f->fr_mr); + return rc; +} + +static void +__frwr_release(struct rpcrdma_mw *r) +{ + int rc; + + rc = ib_dereg_mr(r->r.frmr.fr_mr); + if (rc) + dprintk("RPC: %s: ib_dereg_mr status %i\n", + __func__, rc); + ib_free_fast_reg_page_list(r->r.frmr.fr_pgl); +} + +static int +frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) +{ + struct ib_device_attr *devattr = &ia->ri_devattr; + int depth, delta; + + ia->ri_max_frmr_depth = + min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + devattr->max_fast_reg_page_list_len); + dprintk("RPC: %s: device's max FR page list len = %u\n", + __func__, ia->ri_max_frmr_depth); + + /* Add room for frmr register and invalidate WRs. + * 1. FRMR reg WR for head + * 2. FRMR invalidate WR for head + * 3. N FRMR reg WRs for pagelist + * 4. N FRMR invalidate WRs for pagelist + * 5. FRMR reg WR for tail + * 6. FRMR invalidate WR for tail + * 7. The RDMA_SEND WR + */ + depth = 7; + + /* Calculate N if the device max FRMR depth is smaller than + * RPCRDMA_MAX_DATA_SEGS. + */ + if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) { + delta = RPCRDMA_MAX_DATA_SEGS - ia->ri_max_frmr_depth; + do { + depth += 2; /* FRMR reg + invalidate */ + delta -= ia->ri_max_frmr_depth; + } while (delta > 0); + } + + ep->rep_attr.cap.max_send_wr *= depth; + if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) { + cdata->max_requests = devattr->max_qp_wr / depth; + if (!cdata->max_requests) + return -EINVAL; + ep->rep_attr.cap.max_send_wr = cdata->max_requests * + depth; + } + + return 0; +} + +/* FRWR mode conveys a list of pages per chunk segment. The + * maximum length of that list is the FRWR page list depth. + */ +static size_t +frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + + return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth); +} + +/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */ +static void +frwr_sendcompletion(struct ib_wc *wc) +{ + struct rpcrdma_mw *r; + + if (likely(wc->status == IB_WC_SUCCESS)) + return; + + /* WARNING: Only wr_id and status are reliable at this point */ + r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; + dprintk("RPC: %s: frmr %p (stale), status %d\n", + __func__, r, wc->status); + r->r.frmr.fr_state = FRMR_IS_STALE; +} + +static int +frwr_op_init(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct ib_device *device = r_xprt->rx_ia.ri_id->device; + unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; + struct ib_pd *pd = r_xprt->rx_ia.ri_pd; + int i; + + INIT_LIST_HEAD(&buf->rb_mws); + INIT_LIST_HEAD(&buf->rb_all); + + i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; + dprintk("RPC: %s: initalizing %d FRMRs\n", __func__, i); + + while (i--) { + struct rpcrdma_mw *r; + int rc; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return -ENOMEM; + + rc = __frwr_init(r, pd, device, depth); + if (rc) { + kfree(r); + return rc; + } + + list_add(&r->mw_list, &buf->rb_mws); + list_add(&r->mw_all, &buf->rb_all); + r->mw_sendcompletion = frwr_sendcompletion; + } + + return 0; +} + +/* Post a FAST_REG Work Request to register a memory region + * for remote access via RDMA READ or RDMA WRITE. + */ +static int +frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int nsegs, bool writing) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct ib_device *device = ia->ri_id->device; + enum dma_data_direction direction = rpcrdma_data_dir(writing); + struct rpcrdma_mr_seg *seg1 = seg; + struct rpcrdma_mw *mw = seg1->rl_mw; + struct rpcrdma_frmr *frmr = &mw->r.frmr; + struct ib_mr *mr = frmr->fr_mr; + struct ib_send_wr fastreg_wr, *bad_wr; + u8 key; + int len, pageoff; + int i, rc; + int seg_len; + u64 pa; + int page_no; + + pageoff = offset_in_page(seg1->mr_offset); + seg1->mr_offset -= pageoff; /* start of page */ + seg1->mr_len += pageoff; + len = -pageoff; + if (nsegs > ia->ri_max_frmr_depth) + nsegs = ia->ri_max_frmr_depth; + for (page_no = i = 0; i < nsegs;) { + rpcrdma_map_one(device, seg, direction); + pa = seg->mr_dma; + for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) { + frmr->fr_pgl->page_list[page_no++] = pa; + pa += PAGE_SIZE; + } + len += seg->mr_len; + ++seg; + ++i; + /* Check for holes */ + if ((i < nsegs && offset_in_page(seg->mr_offset)) || + offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) + break; + } + dprintk("RPC: %s: Using frmr %p to map %d segments (%d bytes)\n", + __func__, mw, i, len); + + frmr->fr_state = FRMR_IS_VALID; + + memset(&fastreg_wr, 0, sizeof(fastreg_wr)); + fastreg_wr.wr_id = (unsigned long)(void *)mw; + fastreg_wr.opcode = IB_WR_FAST_REG_MR; + fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma + pageoff; + fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl; + fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; + fastreg_wr.wr.fast_reg.page_list_len = page_no; + fastreg_wr.wr.fast_reg.length = len; + fastreg_wr.wr.fast_reg.access_flags = writing ? + IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : + IB_ACCESS_REMOTE_READ; + key = (u8)(mr->rkey & 0x000000FF); + ib_update_fast_reg_key(mr, ++key); + fastreg_wr.wr.fast_reg.rkey = mr->rkey; + + DECR_CQCOUNT(&r_xprt->rx_ep); + rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr); + if (rc) + goto out_senderr; + + seg1->mr_rkey = mr->rkey; + seg1->mr_base = seg1->mr_dma + pageoff; + seg1->mr_nsegs = i; + seg1->mr_len = len; + return i; + +out_senderr: + dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc); + ib_update_fast_reg_key(mr, --key); + frmr->fr_state = FRMR_IS_INVALID; + while (i--) + rpcrdma_unmap_one(device, --seg); + return rc; +} + +/* Post a LOCAL_INV Work Request to prevent further remote access + * via RDMA READ or RDMA WRITE. + */ +static int +frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_mr_seg *seg1 = seg; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct ib_send_wr invalidate_wr, *bad_wr; + int rc, nsegs = seg->mr_nsegs; + struct ib_device *device; + + seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID; + + memset(&invalidate_wr, 0, sizeof(invalidate_wr)); + invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw; + invalidate_wr.opcode = IB_WR_LOCAL_INV; + invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey; + DECR_CQCOUNT(&r_xprt->rx_ep); + + read_lock(&ia->ri_qplock); + device = ia->ri_id->device; + while (seg1->mr_nsegs--) + rpcrdma_unmap_one(device, seg++); + rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr); + read_unlock(&ia->ri_qplock); + if (rc) + goto out_err; + return nsegs; + +out_err: + /* Force rpcrdma_buffer_get() to retry */ + seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE; + dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc); + return nsegs; +} + +/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in + * an unusable state. Find FRMRs in this state and dereg / reg + * each. FRMRs that are VALID and attached to an rpcrdma_req are + * also torn down. + * + * This gives all in-use FRMRs a fresh rkey and leaves them INVALID. + * + * This is invoked only in the transport connect worker in order + * to serialize with rpcrdma_register_frmr_external(). + */ +static void +frwr_op_reset(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct ib_device *device = r_xprt->rx_ia.ri_id->device; + unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; + struct ib_pd *pd = r_xprt->rx_ia.ri_pd; + struct rpcrdma_mw *r; + int rc; + + list_for_each_entry(r, &buf->rb_all, mw_all) { + if (r->r.frmr.fr_state == FRMR_IS_INVALID) + continue; + + __frwr_release(r); + rc = __frwr_init(r, pd, device, depth); + if (rc) { + dprintk("RPC: %s: mw %p left %s\n", + __func__, r, + (r->r.frmr.fr_state == FRMR_IS_STALE ? + "stale" : "valid")); + continue; + } + + r->r.frmr.fr_state = FRMR_IS_INVALID; + } +} + +static void +frwr_op_destroy(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_mw *r; + + while (!list_empty(&buf->rb_all)) { + r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); + list_del(&r->mw_all); + __frwr_release(r); + kfree(r); + } +} + +const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { + .ro_map = frwr_op_map, + .ro_unmap = frwr_op_unmap, + .ro_open = frwr_op_open, + .ro_maxpages = frwr_op_maxpages, + .ro_init = frwr_op_init, + .ro_reset = frwr_op_reset, + .ro_destroy = frwr_op_destroy, + .ro_displayname = "frwr", +}; diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c new file mode 100644 index 000000000000..ba518af16787 --- /dev/null +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -0,0 +1,94 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + */ + +/* No-op chunk preparation. All client memory is pre-registered. + * Sometimes referred to as ALLPHYSICAL mode. + * + * Physical registration is simple because all client memory is + * pre-registered and never deregistered. This mode is good for + * adapter bring up, but is considered not safe: the server is + * trusted not to abuse its access to client memory not involved + * in RDMA I/O. + */ + +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +static int +physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) +{ + return 0; +} + +/* PHYSICAL memory registration conveys one page per chunk segment. + */ +static size_t +physical_op_maxpages(struct rpcrdma_xprt *r_xprt) +{ + return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + rpcrdma_max_segments(r_xprt)); +} + +static int +physical_op_init(struct rpcrdma_xprt *r_xprt) +{ + return 0; +} + +/* The client's physical memory is already exposed for + * remote access via RDMA READ or RDMA WRITE. + */ +static int +physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int nsegs, bool writing) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + + rpcrdma_map_one(ia->ri_id->device, seg, + rpcrdma_data_dir(writing)); + seg->mr_rkey = ia->ri_bind_mem->rkey; + seg->mr_base = seg->mr_dma; + seg->mr_nsegs = 1; + return 1; +} + +/* Unmap a memory region, but leave it registered. + */ +static int +physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + + read_lock(&ia->ri_qplock); + rpcrdma_unmap_one(ia->ri_id->device, seg); + read_unlock(&ia->ri_qplock); + + return 1; +} + +static void +physical_op_reset(struct rpcrdma_xprt *r_xprt) +{ +} + +static void +physical_op_destroy(struct rpcrdma_buffer *buf) +{ +} + +const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = { + .ro_map = physical_op_map, + .ro_unmap = physical_op_unmap, + .ro_open = physical_op_open, + .ro_maxpages = physical_op_maxpages, + .ro_init = physical_op_init, + .ro_reset = physical_op_reset, + .ro_destroy = physical_op_destroy, + .ro_displayname = "physical", +}; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 91ffde82fa0c..2c53ea9e1b83 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -53,6 +53,14 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif +enum rpcrdma_chunktype { + rpcrdma_noch = 0, + rpcrdma_readch, + rpcrdma_areadch, + rpcrdma_writech, + rpcrdma_replych +}; + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char transfertypes[][12] = { "pure inline", /* no chunks */ @@ -179,6 +187,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, struct rpcrdma_write_array *warray = NULL; struct rpcrdma_write_chunk *cur_wchunk = NULL; __be32 *iptr = headerp->rm_body.rm_chunks; + int (*map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool); if (type == rpcrdma_readch || type == rpcrdma_areadch) { /* a read chunk - server will RDMA Read our memory */ @@ -201,9 +210,9 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, if (nsegs < 0) return nsegs; + map = r_xprt->rx_ia.ri_ops->ro_map; do { - n = rpcrdma_register_external(seg, nsegs, - cur_wchunk != NULL, r_xprt); + n = map(r_xprt, seg, nsegs, cur_wchunk != NULL); if (n <= 0) goto out; if (cur_rchunk) { /* read */ @@ -275,34 +284,13 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, return (unsigned char *)iptr - (unsigned char *)headerp; out: - if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_FRMR) { - for (pos = 0; nchunks--;) - pos += rpcrdma_deregister_external( - &req->rl_segments[pos], r_xprt); - } - return n; -} + if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR) + return n; -/* - * Marshal chunks. This routine returns the header length - * consumed by marshaling. - * - * Returns positive RPC/RDMA header size, or negative errno. - */ - -ssize_t -rpcrdma_marshal_chunks(struct rpc_rqst *rqst, ssize_t result) -{ - struct rpcrdma_req *req = rpcr_to_rdmar(rqst); - struct rpcrdma_msg *headerp = rdmab_to_msg(req->rl_rdmabuf); - - if (req->rl_rtype != rpcrdma_noch) - result = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf, - headerp, req->rl_rtype); - else if (req->rl_wtype != rpcrdma_noch) - result = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf, - headerp, req->rl_wtype); - return result; + for (pos = 0; nchunks--;) + pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt, + &req->rl_segments[pos]); + return n; } /* @@ -397,6 +385,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) char *base; size_t rpclen, padlen; ssize_t hdrlen; + enum rpcrdma_chunktype rtype, wtype; struct rpcrdma_msg *headerp; /* @@ -433,13 +422,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * into pages; otherwise use reply chunks. */ if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst)) - req->rl_wtype = rpcrdma_noch; + wtype = rpcrdma_noch; else if (rqst->rq_rcv_buf.page_len == 0) - req->rl_wtype = rpcrdma_replych; + wtype = rpcrdma_replych; else if (rqst->rq_rcv_buf.flags & XDRBUF_READ) - req->rl_wtype = rpcrdma_writech; + wtype = rpcrdma_writech; else - req->rl_wtype = rpcrdma_replych; + wtype = rpcrdma_replych; /* * Chunks needed for arguments? @@ -456,16 +445,16 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * TBD check NFSv4 setacl */ if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst)) - req->rl_rtype = rpcrdma_noch; + rtype = rpcrdma_noch; else if (rqst->rq_snd_buf.page_len == 0) - req->rl_rtype = rpcrdma_areadch; + rtype = rpcrdma_areadch; else - req->rl_rtype = rpcrdma_readch; + rtype = rpcrdma_readch; /* The following simplification is not true forever */ - if (req->rl_rtype != rpcrdma_noch && req->rl_wtype == rpcrdma_replych) - req->rl_wtype = rpcrdma_noch; - if (req->rl_rtype != rpcrdma_noch && req->rl_wtype != rpcrdma_noch) { + if (rtype != rpcrdma_noch && wtype == rpcrdma_replych) + wtype = rpcrdma_noch; + if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) { dprintk("RPC: %s: cannot marshal multiple chunk lists\n", __func__); return -EIO; @@ -479,7 +468,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * When padding is in use and applies to the transfer, insert * it and change the message type. */ - if (req->rl_rtype == rpcrdma_noch) { + if (rtype == rpcrdma_noch) { padlen = rpcrdma_inline_pullup(rqst, RPCRDMA_INLINE_PAD_VALUE(rqst)); @@ -494,7 +483,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero; headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero; hdrlen += 2 * sizeof(u32); /* extra words in padhdr */ - if (req->rl_wtype != rpcrdma_noch) { + if (wtype != rpcrdma_noch) { dprintk("RPC: %s: invalid chunk list\n", __func__); return -EIO; @@ -515,18 +504,26 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * on receive. Therefore, we request a reply chunk * for non-writes wherever feasible and efficient. */ - if (req->rl_wtype == rpcrdma_noch) - req->rl_wtype = rpcrdma_replych; + if (wtype == rpcrdma_noch) + wtype = rpcrdma_replych; } } - hdrlen = rpcrdma_marshal_chunks(rqst, hdrlen); + if (rtype != rpcrdma_noch) { + hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf, + headerp, rtype); + wtype = rtype; /* simplify dprintk */ + + } else if (wtype != rpcrdma_noch) { + hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf, + headerp, wtype); + } if (hdrlen < 0) return hdrlen; dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd padlen %zd" " headerp 0x%p base 0x%p lkey 0x%x\n", - __func__, transfertypes[req->rl_wtype], hdrlen, rpclen, padlen, + __func__, transfertypes[wtype], hdrlen, rpclen, padlen, headerp, base, rdmab_lkey(req->rl_rdmabuf)); /* diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 2e192baa59f3..54f23b1be986 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -157,12 +157,47 @@ static struct ctl_table sunrpc_table[] = { static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ static void +xprt_rdma_format_addresses4(struct rpc_xprt *xprt, struct sockaddr *sap) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + char buf[20]; + + snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA; +} + +static void +xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + char buf[40]; + + snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA6; +} + +static void xprt_rdma_format_addresses(struct rpc_xprt *xprt) { struct sockaddr *sap = (struct sockaddr *) &rpcx_to_rdmad(xprt).addr; - struct sockaddr_in *sin = (struct sockaddr_in *)sap; - char buf[64]; + char buf[128]; + + switch (sap->sa_family) { + case AF_INET: + xprt_rdma_format_addresses4(xprt, sap); + break; + case AF_INET6: + xprt_rdma_format_addresses6(xprt, sap); + break; + default: + pr_err("rpcrdma: Unrecognized address family\n"); + return; + } (void)rpc_ntop(sap, buf, sizeof(buf)); xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); @@ -170,16 +205,10 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt) snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); - xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - - snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); - snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); - /* netid */ - xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; + xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; } static void @@ -377,7 +406,10 @@ xprt_setup_rdma(struct xprt_create *args) xprt_rdma_connect_worker); xprt_rdma_format_addresses(xprt); - xprt->max_payload = rpcrdma_max_payload(new_xprt); + xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt); + if (xprt->max_payload == 0) + goto out4; + xprt->max_payload <<= PAGE_SHIFT; dprintk("RPC: %s: transport data payload maximum: %zu bytes\n", __func__, xprt->max_payload); @@ -552,8 +584,8 @@ xprt_rdma_free(void *buffer) for (i = 0; req->rl_nchunks;) { --req->rl_nchunks; - i += rpcrdma_deregister_external( - &req->rl_segments[i], r_xprt); + i += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt, + &req->rl_segments[i]); } rpcrdma_buffer_put(req); @@ -579,10 +611,7 @@ xprt_rdma_send_request(struct rpc_task *task) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); int rc = 0; - if (req->rl_niovs == 0) - rc = rpcrdma_marshal_req(rqst); - else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL) - rc = rpcrdma_marshal_chunks(rqst, 0); + rc = rpcrdma_marshal_req(rqst); if (rc < 0) goto failed_marshal; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 124676c13780..4870d272e006 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -50,6 +50,7 @@ #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/prefetch.h> +#include <linux/sunrpc/addr.h> #include <asm/bitops.h> #include "xprt_rdma.h" @@ -62,9 +63,6 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -static void rpcrdma_reset_frmrs(struct rpcrdma_ia *); -static void rpcrdma_reset_fmrs(struct rpcrdma_ia *); - /* * internal functions */ @@ -188,7 +186,7 @@ static const char * const wc_status[] = { "remote access error", "remote operation error", "transport retry counter exceeded", - "RNR retrycounter exceeded", + "RNR retry counter exceeded", "local RDD violation error", "remove invalid RD request", "operation aborted", @@ -206,21 +204,17 @@ static const char * const wc_status[] = { static void rpcrdma_sendcq_process_wc(struct ib_wc *wc) { - if (likely(wc->status == IB_WC_SUCCESS)) - return; - /* WARNING: Only wr_id and status are reliable at this point */ - if (wc->wr_id == 0ULL) { - if (wc->status != IB_WC_WR_FLUSH_ERR) + if (wc->wr_id == RPCRDMA_IGNORE_COMPLETION) { + if (wc->status != IB_WC_SUCCESS && + wc->status != IB_WC_WR_FLUSH_ERR) pr_err("RPC: %s: SEND: %s\n", __func__, COMPLETION_MSG(wc->status)); } else { struct rpcrdma_mw *r; r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; - r->r.frmr.fr_state = FRMR_IS_STALE; - pr_err("RPC: %s: frmr %p (stale): %s\n", - __func__, r, COMPLETION_MSG(wc->status)); + r->mw_sendcompletion(wc); } } @@ -424,7 +418,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) struct rpcrdma_ia *ia = &xprt->rx_ia; struct rpcrdma_ep *ep = &xprt->rx_ep; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - struct sockaddr_in *addr = (struct sockaddr_in *) &ep->rep_remote_addr; + struct sockaddr *sap = (struct sockaddr *)&ep->rep_remote_addr; #endif struct ib_qp_attr *attr = &ia->ri_qp_attr; struct ib_qp_init_attr *iattr = &ia->ri_qp_init_attr; @@ -480,9 +474,8 @@ connected: wake_up_all(&ep->rep_connect_wait); /*FALLTHROUGH*/ default: - dprintk("RPC: %s: %pI4:%u (ep 0x%p): %s\n", - __func__, &addr->sin_addr.s_addr, - ntohs(addr->sin_port), ep, + dprintk("RPC: %s: %pIS:%u (ep 0x%p): %s\n", + __func__, sap, rpc_get_port(sap), ep, CONNECTION_MSG(event->event)); break; } @@ -491,19 +484,16 @@ connected: if (connstate == 1) { int ird = attr->max_dest_rd_atomic; int tird = ep->rep_remote_cma.responder_resources; - printk(KERN_INFO "rpcrdma: connection to %pI4:%u " - "on %s, memreg %d slots %d ird %d%s\n", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), + + pr_info("rpcrdma: connection to %pIS:%u on %s, memreg '%s', %d credits, %d responders%s\n", + sap, rpc_get_port(sap), ia->ri_id->device->name, - ia->ri_memreg_strategy, + ia->ri_ops->ro_displayname, xprt->rx_buf.rb_max_requests, ird, ird < 4 && ird < tird / 2 ? " (low!)" : ""); } else if (connstate < 0) { - printk(KERN_INFO "rpcrdma: connection to %pI4:%u closed (%d)\n", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), - connstate); + pr_info("rpcrdma: connection to %pIS:%u closed (%d)\n", + sap, rpc_get_port(sap), connstate); } #endif @@ -621,17 +611,13 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) if (memreg == RPCRDMA_FRMR) { /* Requires both frmr reg and local dma lkey */ - if ((devattr->device_cap_flags & + if (((devattr->device_cap_flags & (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) != - (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) { + (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) || + (devattr->max_fast_reg_page_list_len == 0)) { dprintk("RPC: %s: FRMR registration " "not supported by HCA\n", __func__); memreg = RPCRDMA_MTHCAFMR; - } else { - /* Mind the ia limit on FRMR page list depth */ - ia->ri_max_frmr_depth = min_t(unsigned int, - RPCRDMA_MAX_DATA_SEGS, - devattr->max_fast_reg_page_list_len); } } if (memreg == RPCRDMA_MTHCAFMR) { @@ -652,13 +638,16 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) */ switch (memreg) { case RPCRDMA_FRMR: + ia->ri_ops = &rpcrdma_frwr_memreg_ops; break; case RPCRDMA_ALLPHYSICAL: + ia->ri_ops = &rpcrdma_physical_memreg_ops; mem_priv = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; goto register_setup; case RPCRDMA_MTHCAFMR: + ia->ri_ops = &rpcrdma_fmr_memreg_ops; if (ia->ri_have_dma_lkey) break; mem_priv = IB_ACCESS_LOCAL_WRITE; @@ -678,8 +667,8 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) rc = -ENOMEM; goto out3; } - dprintk("RPC: %s: memory registration strategy is %d\n", - __func__, memreg); + dprintk("RPC: %s: memory registration strategy is '%s'\n", + __func__, ia->ri_ops->ro_displayname); /* Else will do memory reg/dereg for each chunk */ ia->ri_memreg_strategy = memreg; @@ -743,49 +732,11 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall; ep->rep_attr.qp_context = ep; - /* send_cq and recv_cq initialized below */ ep->rep_attr.srq = NULL; ep->rep_attr.cap.max_send_wr = cdata->max_requests; - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: { - int depth = 7; - - /* Add room for frmr register and invalidate WRs. - * 1. FRMR reg WR for head - * 2. FRMR invalidate WR for head - * 3. N FRMR reg WRs for pagelist - * 4. N FRMR invalidate WRs for pagelist - * 5. FRMR reg WR for tail - * 6. FRMR invalidate WR for tail - * 7. The RDMA_SEND WR - */ - - /* Calculate N if the device max FRMR depth is smaller than - * RPCRDMA_MAX_DATA_SEGS. - */ - if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) { - int delta = RPCRDMA_MAX_DATA_SEGS - - ia->ri_max_frmr_depth; - - do { - depth += 2; /* FRMR reg + invalidate */ - delta -= ia->ri_max_frmr_depth; - } while (delta > 0); - - } - ep->rep_attr.cap.max_send_wr *= depth; - if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) { - cdata->max_requests = devattr->max_qp_wr / depth; - if (!cdata->max_requests) - return -EINVAL; - ep->rep_attr.cap.max_send_wr = cdata->max_requests * - depth; - } - break; - } - default: - break; - } + rc = ia->ri_ops->ro_open(ia, ep, cdata); + if (rc) + return rc; ep->rep_attr.cap.max_recv_wr = cdata->max_requests; ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2); ep->rep_attr.cap.max_recv_sge = 1; @@ -944,21 +895,9 @@ retry: rpcrdma_ep_disconnect(ep, ia); rpcrdma_flush_cqs(ep); - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: - rpcrdma_reset_frmrs(ia); - break; - case RPCRDMA_MTHCAFMR: - rpcrdma_reset_fmrs(ia); - break; - case RPCRDMA_ALLPHYSICAL: - break; - default: - rc = -EIO; - goto out; - } - xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); + ia->ri_ops->ro_reset(xprt); + id = rpcrdma_create_id(xprt, ia, (struct sockaddr *)&xprt->rx_data.addr); if (IS_ERR(id)) { @@ -1123,91 +1062,6 @@ out: return ERR_PTR(rc); } -static int -rpcrdma_init_fmrs(struct rpcrdma_ia *ia, struct rpcrdma_buffer *buf) -{ - int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; - struct ib_fmr_attr fmr_attr = { - .max_pages = RPCRDMA_MAX_DATA_SEGS, - .max_maps = 1, - .page_shift = PAGE_SHIFT - }; - struct rpcrdma_mw *r; - int i, rc; - - i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; - dprintk("RPC: %s: initalizing %d FMRs\n", __func__, i); - - while (i--) { - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (r == NULL) - return -ENOMEM; - - r->r.fmr = ib_alloc_fmr(ia->ri_pd, mr_access_flags, &fmr_attr); - if (IS_ERR(r->r.fmr)) { - rc = PTR_ERR(r->r.fmr); - dprintk("RPC: %s: ib_alloc_fmr failed %i\n", - __func__, rc); - goto out_free; - } - - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - return 0; - -out_free: - kfree(r); - return rc; -} - -static int -rpcrdma_init_frmrs(struct rpcrdma_ia *ia, struct rpcrdma_buffer *buf) -{ - struct rpcrdma_frmr *f; - struct rpcrdma_mw *r; - int i, rc; - - i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; - dprintk("RPC: %s: initalizing %d FRMRs\n", __func__, i); - - while (i--) { - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (r == NULL) - return -ENOMEM; - f = &r->r.frmr; - - f->fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd, - ia->ri_max_frmr_depth); - if (IS_ERR(f->fr_mr)) { - rc = PTR_ERR(f->fr_mr); - dprintk("RPC: %s: ib_alloc_fast_reg_mr " - "failed %i\n", __func__, rc); - goto out_free; - } - - f->fr_pgl = ib_alloc_fast_reg_page_list(ia->ri_id->device, - ia->ri_max_frmr_depth); - if (IS_ERR(f->fr_pgl)) { - rc = PTR_ERR(f->fr_pgl); - dprintk("RPC: %s: ib_alloc_fast_reg_page_list " - "failed %i\n", __func__, rc); - - ib_dereg_mr(f->fr_mr); - goto out_free; - } - - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - - return 0; - -out_free: - kfree(r); - return rc; -} - int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) { @@ -1244,22 +1098,9 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) buf->rb_recv_bufs = (struct rpcrdma_rep **) p; p = (char *) &buf->rb_recv_bufs[buf->rb_max_requests]; - INIT_LIST_HEAD(&buf->rb_mws); - INIT_LIST_HEAD(&buf->rb_all); - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: - rc = rpcrdma_init_frmrs(ia, buf); - if (rc) - goto out; - break; - case RPCRDMA_MTHCAFMR: - rc = rpcrdma_init_fmrs(ia, buf); - if (rc) - goto out; - break; - default: - break; - } + rc = ia->ri_ops->ro_init(r_xprt); + if (rc) + goto out; for (i = 0; i < buf->rb_max_requests; i++) { struct rpcrdma_req *req; @@ -1311,47 +1152,6 @@ rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req) kfree(req); } -static void -rpcrdma_destroy_fmrs(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - int rc; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - list_del(&r->mw_list); - - rc = ib_dealloc_fmr(r->r.fmr); - if (rc) - dprintk("RPC: %s: ib_dealloc_fmr failed %i\n", - __func__, rc); - - kfree(r); - } -} - -static void -rpcrdma_destroy_frmrs(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - int rc; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - list_del(&r->mw_list); - - rc = ib_dereg_mr(r->r.frmr.fr_mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr failed %i\n", - __func__, rc); - ib_free_fast_reg_page_list(r->r.frmr.fr_pgl); - - kfree(r); - } -} - void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { @@ -1372,104 +1172,11 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) rpcrdma_destroy_req(ia, buf->rb_send_bufs[i]); } - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: - rpcrdma_destroy_frmrs(buf); - break; - case RPCRDMA_MTHCAFMR: - rpcrdma_destroy_fmrs(buf); - break; - default: - break; - } + ia->ri_ops->ro_destroy(buf); kfree(buf->rb_pool); } -/* After a disconnect, unmap all FMRs. - * - * This is invoked only in the transport connect worker in order - * to serialize with rpcrdma_register_fmr_external(). - */ -static void -rpcrdma_reset_fmrs(struct rpcrdma_ia *ia) -{ - struct rpcrdma_xprt *r_xprt = - container_of(ia, struct rpcrdma_xprt, rx_ia); - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct list_head *pos; - struct rpcrdma_mw *r; - LIST_HEAD(l); - int rc; - - list_for_each(pos, &buf->rb_all) { - r = list_entry(pos, struct rpcrdma_mw, mw_all); - - INIT_LIST_HEAD(&l); - list_add(&r->r.fmr->list, &l); - rc = ib_unmap_fmr(&l); - if (rc) - dprintk("RPC: %s: ib_unmap_fmr failed %i\n", - __func__, rc); - } -} - -/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in - * an unusable state. Find FRMRs in this state and dereg / reg - * each. FRMRs that are VALID and attached to an rpcrdma_req are - * also torn down. - * - * This gives all in-use FRMRs a fresh rkey and leaves them INVALID. - * - * This is invoked only in the transport connect worker in order - * to serialize with rpcrdma_register_frmr_external(). - */ -static void -rpcrdma_reset_frmrs(struct rpcrdma_ia *ia) -{ - struct rpcrdma_xprt *r_xprt = - container_of(ia, struct rpcrdma_xprt, rx_ia); - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct list_head *pos; - struct rpcrdma_mw *r; - int rc; - - list_for_each(pos, &buf->rb_all) { - r = list_entry(pos, struct rpcrdma_mw, mw_all); - - if (r->r.frmr.fr_state == FRMR_IS_INVALID) - continue; - - rc = ib_dereg_mr(r->r.frmr.fr_mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr failed %i\n", - __func__, rc); - ib_free_fast_reg_page_list(r->r.frmr.fr_pgl); - - r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd, - ia->ri_max_frmr_depth); - if (IS_ERR(r->r.frmr.fr_mr)) { - rc = PTR_ERR(r->r.frmr.fr_mr); - dprintk("RPC: %s: ib_alloc_fast_reg_mr" - " failed %i\n", __func__, rc); - continue; - } - r->r.frmr.fr_pgl = ib_alloc_fast_reg_page_list( - ia->ri_id->device, - ia->ri_max_frmr_depth); - if (IS_ERR(r->r.frmr.fr_pgl)) { - rc = PTR_ERR(r->r.frmr.fr_pgl); - dprintk("RPC: %s: " - "ib_alloc_fast_reg_page_list " - "failed %i\n", __func__, rc); - - ib_dereg_mr(r->r.frmr.fr_mr); - continue; - } - r->r.frmr.fr_state = FRMR_IS_INVALID; - } -} - /* "*mw" can be NULL when rpcrdma_buffer_get_mrs() fails, leaving * some req segments uninitialized. */ @@ -1509,7 +1216,7 @@ rpcrdma_buffer_put_sendbuf(struct rpcrdma_req *req, struct rpcrdma_buffer *buf) } } -/* rpcrdma_unmap_one() was already done by rpcrdma_deregister_frmr_external(). +/* rpcrdma_unmap_one() was already done during deregistration. * Redo only the ib_post_send(). */ static void @@ -1729,6 +1436,14 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) * Wrappers for internal-use kmalloc memory registration, used by buffer code. */ +void +rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg) +{ + dprintk("RPC: map_one: offset %p iova %llx len %zu\n", + seg->mr_offset, + (unsigned long long)seg->mr_dma, seg->mr_dmalen); +} + static int rpcrdma_register_internal(struct rpcrdma_ia *ia, void *va, int len, struct ib_mr **mrp, struct ib_sge *iov) @@ -1854,287 +1569,6 @@ rpcrdma_free_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) } /* - * Wrappers for chunk registration, shared by read/write chunk code. - */ - -static void -rpcrdma_map_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg, int writing) -{ - seg->mr_dir = writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; - seg->mr_dmalen = seg->mr_len; - if (seg->mr_page) - seg->mr_dma = ib_dma_map_page(ia->ri_id->device, - seg->mr_page, offset_in_page(seg->mr_offset), - seg->mr_dmalen, seg->mr_dir); - else - seg->mr_dma = ib_dma_map_single(ia->ri_id->device, - seg->mr_offset, - seg->mr_dmalen, seg->mr_dir); - if (ib_dma_mapping_error(ia->ri_id->device, seg->mr_dma)) { - dprintk("RPC: %s: mr_dma %llx mr_offset %p mr_dma_len %zu\n", - __func__, - (unsigned long long)seg->mr_dma, - seg->mr_offset, seg->mr_dmalen); - } -} - -static void -rpcrdma_unmap_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg) -{ - if (seg->mr_page) - ib_dma_unmap_page(ia->ri_id->device, - seg->mr_dma, seg->mr_dmalen, seg->mr_dir); - else - ib_dma_unmap_single(ia->ri_id->device, - seg->mr_dma, seg->mr_dmalen, seg->mr_dir); -} - -static int -rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg, - int *nsegs, int writing, struct rpcrdma_ia *ia, - struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_mr_seg *seg1 = seg; - struct rpcrdma_mw *mw = seg1->rl_mw; - struct rpcrdma_frmr *frmr = &mw->r.frmr; - struct ib_mr *mr = frmr->fr_mr; - struct ib_send_wr fastreg_wr, *bad_wr; - u8 key; - int len, pageoff; - int i, rc; - int seg_len; - u64 pa; - int page_no; - - pageoff = offset_in_page(seg1->mr_offset); - seg1->mr_offset -= pageoff; /* start of page */ - seg1->mr_len += pageoff; - len = -pageoff; - if (*nsegs > ia->ri_max_frmr_depth) - *nsegs = ia->ri_max_frmr_depth; - for (page_no = i = 0; i < *nsegs;) { - rpcrdma_map_one(ia, seg, writing); - pa = seg->mr_dma; - for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) { - frmr->fr_pgl->page_list[page_no++] = pa; - pa += PAGE_SIZE; - } - len += seg->mr_len; - ++seg; - ++i; - /* Check for holes */ - if ((i < *nsegs && offset_in_page(seg->mr_offset)) || - offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) - break; - } - dprintk("RPC: %s: Using frmr %p to map %d segments\n", - __func__, mw, i); - - frmr->fr_state = FRMR_IS_VALID; - - memset(&fastreg_wr, 0, sizeof(fastreg_wr)); - fastreg_wr.wr_id = (unsigned long)(void *)mw; - fastreg_wr.opcode = IB_WR_FAST_REG_MR; - fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma; - fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl; - fastreg_wr.wr.fast_reg.page_list_len = page_no; - fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; - fastreg_wr.wr.fast_reg.length = page_no << PAGE_SHIFT; - if (fastreg_wr.wr.fast_reg.length < len) { - rc = -EIO; - goto out_err; - } - - /* Bump the key */ - key = (u8)(mr->rkey & 0x000000FF); - ib_update_fast_reg_key(mr, ++key); - - fastreg_wr.wr.fast_reg.access_flags = (writing ? - IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : - IB_ACCESS_REMOTE_READ); - fastreg_wr.wr.fast_reg.rkey = mr->rkey; - DECR_CQCOUNT(&r_xprt->rx_ep); - - rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr); - if (rc) { - dprintk("RPC: %s: failed ib_post_send for register," - " status %i\n", __func__, rc); - ib_update_fast_reg_key(mr, --key); - goto out_err; - } else { - seg1->mr_rkey = mr->rkey; - seg1->mr_base = seg1->mr_dma + pageoff; - seg1->mr_nsegs = i; - seg1->mr_len = len; - } - *nsegs = i; - return 0; -out_err: - frmr->fr_state = FRMR_IS_INVALID; - while (i--) - rpcrdma_unmap_one(ia, --seg); - return rc; -} - -static int -rpcrdma_deregister_frmr_external(struct rpcrdma_mr_seg *seg, - struct rpcrdma_ia *ia, struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_mr_seg *seg1 = seg; - struct ib_send_wr invalidate_wr, *bad_wr; - int rc; - - seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID; - - memset(&invalidate_wr, 0, sizeof invalidate_wr); - invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw; - invalidate_wr.opcode = IB_WR_LOCAL_INV; - invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey; - DECR_CQCOUNT(&r_xprt->rx_ep); - - read_lock(&ia->ri_qplock); - while (seg1->mr_nsegs--) - rpcrdma_unmap_one(ia, seg++); - rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr); - read_unlock(&ia->ri_qplock); - if (rc) { - /* Force rpcrdma_buffer_get() to retry */ - seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE; - dprintk("RPC: %s: failed ib_post_send for invalidate," - " status %i\n", __func__, rc); - } - return rc; -} - -static int -rpcrdma_register_fmr_external(struct rpcrdma_mr_seg *seg, - int *nsegs, int writing, struct rpcrdma_ia *ia) -{ - struct rpcrdma_mr_seg *seg1 = seg; - u64 physaddrs[RPCRDMA_MAX_DATA_SEGS]; - int len, pageoff, i, rc; - - pageoff = offset_in_page(seg1->mr_offset); - seg1->mr_offset -= pageoff; /* start of page */ - seg1->mr_len += pageoff; - len = -pageoff; - if (*nsegs > RPCRDMA_MAX_DATA_SEGS) - *nsegs = RPCRDMA_MAX_DATA_SEGS; - for (i = 0; i < *nsegs;) { - rpcrdma_map_one(ia, seg, writing); - physaddrs[i] = seg->mr_dma; - len += seg->mr_len; - ++seg; - ++i; - /* Check for holes */ - if ((i < *nsegs && offset_in_page(seg->mr_offset)) || - offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) - break; - } - rc = ib_map_phys_fmr(seg1->rl_mw->r.fmr, physaddrs, i, seg1->mr_dma); - if (rc) { - dprintk("RPC: %s: failed ib_map_phys_fmr " - "%u@0x%llx+%i (%d)... status %i\n", __func__, - len, (unsigned long long)seg1->mr_dma, - pageoff, i, rc); - while (i--) - rpcrdma_unmap_one(ia, --seg); - } else { - seg1->mr_rkey = seg1->rl_mw->r.fmr->rkey; - seg1->mr_base = seg1->mr_dma + pageoff; - seg1->mr_nsegs = i; - seg1->mr_len = len; - } - *nsegs = i; - return rc; -} - -static int -rpcrdma_deregister_fmr_external(struct rpcrdma_mr_seg *seg, - struct rpcrdma_ia *ia) -{ - struct rpcrdma_mr_seg *seg1 = seg; - LIST_HEAD(l); - int rc; - - list_add(&seg1->rl_mw->r.fmr->list, &l); - rc = ib_unmap_fmr(&l); - read_lock(&ia->ri_qplock); - while (seg1->mr_nsegs--) - rpcrdma_unmap_one(ia, seg++); - read_unlock(&ia->ri_qplock); - if (rc) - dprintk("RPC: %s: failed ib_unmap_fmr," - " status %i\n", __func__, rc); - return rc; -} - -int -rpcrdma_register_external(struct rpcrdma_mr_seg *seg, - int nsegs, int writing, struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - int rc = 0; - - switch (ia->ri_memreg_strategy) { - - case RPCRDMA_ALLPHYSICAL: - rpcrdma_map_one(ia, seg, writing); - seg->mr_rkey = ia->ri_bind_mem->rkey; - seg->mr_base = seg->mr_dma; - seg->mr_nsegs = 1; - nsegs = 1; - break; - - /* Registration using frmr registration */ - case RPCRDMA_FRMR: - rc = rpcrdma_register_frmr_external(seg, &nsegs, writing, ia, r_xprt); - break; - - /* Registration using fmr memory registration */ - case RPCRDMA_MTHCAFMR: - rc = rpcrdma_register_fmr_external(seg, &nsegs, writing, ia); - break; - - default: - return -EIO; - } - if (rc) - return rc; - - return nsegs; -} - -int -rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg, - struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - int nsegs = seg->mr_nsegs, rc; - - switch (ia->ri_memreg_strategy) { - - case RPCRDMA_ALLPHYSICAL: - read_lock(&ia->ri_qplock); - rpcrdma_unmap_one(ia, seg); - read_unlock(&ia->ri_qplock); - break; - - case RPCRDMA_FRMR: - rc = rpcrdma_deregister_frmr_external(seg, ia, r_xprt); - break; - - case RPCRDMA_MTHCAFMR: - rc = rpcrdma_deregister_fmr_external(seg, ia); - break; - - default: - break; - } - return nsegs; -} - -/* * Prepost any receive buffer, then post send. * * Receive buffer is donated to hardware, reclaimed upon recv completion. @@ -2156,7 +1590,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, } send_wr.next = NULL; - send_wr.wr_id = 0ULL; /* no send cookie */ + send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION; send_wr.sg_list = req->rl_send_iov; send_wr.num_sge = req->rl_niovs; send_wr.opcode = IB_WR_SEND; @@ -2215,43 +1649,24 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia, return rc; } -/* Physical mapping means one Read/Write list entry per-page. - * All list entries must fit within an inline buffer - * - * NB: The server must return a Write list for NFS READ, - * which has the same constraint. Factor in the inline - * rsize as well. +/* How many chunk list items fit within our inline buffers? */ -static size_t -rpcrdma_physical_max_payload(struct rpcrdma_xprt *r_xprt) +unsigned int +rpcrdma_max_segments(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data; - unsigned int inline_size, pages; + int bytes, segments; - inline_size = min_t(unsigned int, - cdata->inline_wsize, cdata->inline_rsize); - inline_size -= RPCRDMA_HDRLEN_MIN; - pages = inline_size / sizeof(struct rpcrdma_segment); - return pages << PAGE_SHIFT; -} - -static size_t -rpcrdma_mr_max_payload(struct rpcrdma_xprt *r_xprt) -{ - return RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT; -} - -size_t -rpcrdma_max_payload(struct rpcrdma_xprt *r_xprt) -{ - size_t result; - - switch (r_xprt->rx_ia.ri_memreg_strategy) { - case RPCRDMA_ALLPHYSICAL: - result = rpcrdma_physical_max_payload(r_xprt); - break; - default: - result = rpcrdma_mr_max_payload(r_xprt); + bytes = min_t(unsigned int, cdata->inline_wsize, cdata->inline_rsize); + bytes -= RPCRDMA_HDRLEN_MIN; + if (bytes < sizeof(struct rpcrdma_segment) * 2) { + pr_warn("RPC: %s: inline threshold too small\n", + __func__); + return 0; } - return result; + + segments = 1 << (fls(bytes / sizeof(struct rpcrdma_segment)) - 1); + dprintk("RPC: %s: max chunk list size = %d segments\n", + __func__, segments); + return segments; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0a16fb6f0885..78e0b8beaa36 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -60,6 +60,7 @@ * Interface Adapter -- one per transport instance */ struct rpcrdma_ia { + const struct rpcrdma_memreg_ops *ri_ops; rwlock_t ri_qplock; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; @@ -105,6 +106,10 @@ struct rpcrdma_ep { #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) +/* Force completion handler to ignore the signal + */ +#define RPCRDMA_IGNORE_COMPLETION (0ULL) + /* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV * * The below structure appears at the front of a large region of kmalloc'd @@ -143,14 +148,6 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) return (struct rpcrdma_msg *)rb->rg_base; } -enum rpcrdma_chunktype { - rpcrdma_noch = 0, - rpcrdma_readch, - rpcrdma_areadch, - rpcrdma_writech, - rpcrdma_replych -}; - /* * struct rpcrdma_rep -- this structure encapsulates state required to recv * and complete a reply, asychronously. It needs several pieces of @@ -213,6 +210,7 @@ struct rpcrdma_mw { struct ib_fmr *fmr; struct rpcrdma_frmr frmr; } r; + void (*mw_sendcompletion)(struct ib_wc *); struct list_head mw_list; struct list_head mw_all; }; @@ -258,7 +256,6 @@ struct rpcrdma_req { unsigned int rl_niovs; /* 0, 2 or 4 */ unsigned int rl_nchunks; /* non-zero if chunks */ unsigned int rl_connect_cookie; /* retry detection */ - enum rpcrdma_chunktype rl_rtype, rl_wtype; struct rpcrdma_buffer *rl_buffer; /* home base for this structure */ struct rpcrdma_rep *rl_reply;/* holder for reply buffer */ struct ib_sge rl_send_iov[4]; /* for active requests */ @@ -340,6 +337,29 @@ struct rpcrdma_stats { }; /* + * Per-registration mode operations + */ +struct rpcrdma_xprt; +struct rpcrdma_memreg_ops { + int (*ro_map)(struct rpcrdma_xprt *, + struct rpcrdma_mr_seg *, int, bool); + int (*ro_unmap)(struct rpcrdma_xprt *, + struct rpcrdma_mr_seg *); + int (*ro_open)(struct rpcrdma_ia *, + struct rpcrdma_ep *, + struct rpcrdma_create_data_internal *); + size_t (*ro_maxpages)(struct rpcrdma_xprt *); + int (*ro_init)(struct rpcrdma_xprt *); + void (*ro_reset)(struct rpcrdma_xprt *); + void (*ro_destroy)(struct rpcrdma_buffer *); + const char *ro_displayname; +}; + +extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops; +extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops; +extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops; + +/* * RPCRDMA transport -- encapsulates the structures above for * integration with RPC. * @@ -398,16 +418,56 @@ void rpcrdma_buffer_put(struct rpcrdma_req *); void rpcrdma_recv_buffer_get(struct rpcrdma_req *); void rpcrdma_recv_buffer_put(struct rpcrdma_rep *); -int rpcrdma_register_external(struct rpcrdma_mr_seg *, - int, int, struct rpcrdma_xprt *); -int rpcrdma_deregister_external(struct rpcrdma_mr_seg *, - struct rpcrdma_xprt *); - struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *, size_t, gfp_t); void rpcrdma_free_regbuf(struct rpcrdma_ia *, struct rpcrdma_regbuf *); +unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *); + +/* + * Wrappers for chunk registration, shared by read/write chunk code. + */ + +void rpcrdma_mapping_error(struct rpcrdma_mr_seg *); + +static inline enum dma_data_direction +rpcrdma_data_dir(bool writing) +{ + return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; +} + +static inline void +rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg, + enum dma_data_direction direction) +{ + seg->mr_dir = direction; + seg->mr_dmalen = seg->mr_len; + + if (seg->mr_page) + seg->mr_dma = ib_dma_map_page(device, + seg->mr_page, offset_in_page(seg->mr_offset), + seg->mr_dmalen, seg->mr_dir); + else + seg->mr_dma = ib_dma_map_single(device, + seg->mr_offset, + seg->mr_dmalen, seg->mr_dir); + + if (ib_dma_mapping_error(device, seg->mr_dma)) + rpcrdma_mapping_error(seg); +} + +static inline void +rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg) +{ + if (seg->mr_page) + ib_dma_unmap_page(device, + seg->mr_dma, seg->mr_dmalen, seg->mr_dir); + else + ib_dma_unmap_single(device, + seg->mr_dma, seg->mr_dmalen, seg->mr_dir); +} + /* * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c */ @@ -418,9 +478,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); /* * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c */ -ssize_t rpcrdma_marshal_chunks(struct rpc_rqst *, ssize_t); int rpcrdma_marshal_req(struct rpc_rqst *); -size_t rpcrdma_max_payload(struct rpcrdma_xprt *); /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; diff --git a/net/tipc/link.c b/net/tipc/link.c index a4cf364316de..14f09b3cb87c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -464,10 +464,11 @@ void tipc_link_reset(struct tipc_link *l_ptr) /* Clean up all queues, except inputq: */ __skb_queue_purge(&l_ptr->outqueue); __skb_queue_purge(&l_ptr->deferred_queue); - skb_queue_splice_init(&l_ptr->wakeupq, &l_ptr->inputq); - if (!skb_queue_empty(&l_ptr->inputq)) + if (!owner->inputq) + owner->inputq = &l_ptr->inputq; + skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq); + if (!skb_queue_empty(owner->inputq)) owner->action_flags |= TIPC_MSG_EVT; - owner->inputq = &l_ptr->inputq; l_ptr->next_out = NULL; l_ptr->unacked_window = 0; l_ptr->checkpoint = 1; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index be2501538011..b6f84f6a2a09 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4400,6 +4400,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; + /* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT + * as userspace might just pass through the capabilities from the IEs + * directly, rather than enforcing this restriction and returning an + * error in this case. + */ + if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { + params.ht_capa = NULL; + params.vht_capa = NULL; + } + /* When you run into this, adjust the code below for the new flag */ BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index cee479bc655c..638af0655aaf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2269,11 +2269,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { - dst_release(dst); - xfrm_pols_put(pols, drop_pols); XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - - return ERR_PTR(-EREMOTE); + err = -EREMOTE; + goto error; } err = -EAGAIN; @@ -2324,7 +2322,8 @@ nopol: error: dst_release(dst); dropdst: - dst_release(dst_orig); + if (!(flags & XFRM_LOOKUP_KEEP_DST_REF)) + dst_release(dst_orig); xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } @@ -2338,7 +2337,8 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, - flags | XFRM_LOOKUP_QUEUE); + flags | XFRM_LOOKUP_QUEUE | + XFRM_LOOKUP_KEEP_DST_REF); if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); |