diff options
Diffstat (limited to 'net')
86 files changed, 992 insertions, 579 deletions
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 38aa6345bdfa..b718db2085b2 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -16,7 +16,7 @@ #include <linux/module.h> /** - * p9_release_req_pages - Release pages after the transaction. + * p9_release_pages - Release pages after the transaction. */ void p9_release_pages(struct page **pages, int nr_pages) { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 0cfba919d167..848969fe7979 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1092,8 +1092,8 @@ static struct p9_trans_module p9_fd_trans = { }; /** - * p9_poll_proc - poll worker thread - * @a: thread state and arguments + * p9_poll_workfn - poll worker thread + * @work: work queue * * polls all v9fs transports for new events and queues the appropriate * work to the work queue diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 6d8e3031978f..3d414acb7015 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -68,8 +68,6 @@ * @pd: Protection Domain pointer * @qp: Queue Pair pointer * @cq: Completion Queue pointer - * @dm_mr: DMA Memory Region pointer - * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events * @privport: Whether a privileged port may be used * @port: The port to use @@ -632,7 +630,7 @@ static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma) } /** - * trans_create_rdma - Transport method for creating atransport instance + * rdma_create_trans - Transport method for creating a transport instance * @client: client instance * @addr: IP address string * @args: Mount options string diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 3aa5a93ad107..4d0372263e5d 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -60,7 +60,6 @@ static atomic_t vp_pinned = ATOMIC_INIT(0); /** * struct virtio_chan - per-instance transport information - * @initialized: whether the channel is initialized * @inuse: whether the channel is in use * @lock: protects multiple elements within this structure * @client: client instance @@ -385,8 +384,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, * @uidata: user bffer that should be ued for zero copy read * @uodata: user buffer that shoud be user for zero copy write * @inlen: read buffer size - * @olen: write buffer size - * @hdrlen: reader header size, This is the size of response protocol data + * @outlen: write buffer size + * @in_hdr_len: reader header size, This is the size of response protocol data * */ static int diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 086a4abdfa7c..0f19960390a6 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -485,7 +485,7 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, static int xen_9pfs_front_resume(struct xenbus_device *dev) { - dev_warn(&dev->dev, "suspsend/resume unsupported\n"); + dev_warn(&dev->dev, "suspend/resume unsupported\n"); return 0; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 01d5d20a6eb1..3138a869b5c0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; #include <linux/module.h> #include <linux/init.h> +/* Hardening for Spectre-v1 */ +#include <linux/nospec.h> + #include "lec.h" #include "lec_arpc.h" #include "resources.h" @@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); if (bytes_left != 0) pr_info("copy from user failed for %d bytes\n", bytes_left); - if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF || - !dev_lec[ioc_data.dev_num]) + if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF) + return -EINVAL; + ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF); + if (!dev_lec[ioc_data.dev_num]) return -EINVAL; vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL); if (!vpriv) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 82c1a6f430b3..5bb6681fa91e 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -518,8 +518,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return -ELOOP; } - /* Device is already being bridged */ - if (br_port_exists(dev)) + /* Device has master upper dev */ + if (netdev_master_upper_dev_get(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 032e0fe45940..28a4c3490359 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info, { unsigned int size = info->entries_size; const void *entries = info->entries; - int ret; newinfo->entries_size = size; - - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); - if (ret) - return ret; + if (info->nentries) { + int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, + info->nentries); + if (ret) + return ret; + } return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 53ecda10b790..13e2ae6be620 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -174,7 +174,7 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow, flow == CAIF_CTRLCMD_DEINIT_RSP ? "CLOSE/DEINIT" : flow == CAIF_CTRLCMD_INIT_FAIL_RSP ? "OPEN_FAIL" : flow == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ? - "REMOTE_SHUTDOWN" : "UKNOWN CTRL COMMAND"); + "REMOTE_SHUTDOWN" : "UNKNOWN CTRL COMMAND"); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index fcb40c12b1f8..3b3d33ea9ed8 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2569,6 +2569,11 @@ static int try_write(struct ceph_connection *con) int ret = 1; dout("try_write start %p state %lu\n", con, con->state); + if (con->state != CON_STATE_PREOPEN && + con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN) + return 0; more: dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes); @@ -2594,6 +2599,8 @@ more: } more_kvec: + BUG_ON(!con->sock); + /* kvec data queued? */ if (con->out_kvec_left) { ret = write_partial_kvec(con); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index b3dac24412d3..21ac6e3b96bb 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -209,6 +209,14 @@ static void reopen_session(struct ceph_mon_client *monc) __open_session(monc); } +static void un_backoff(struct ceph_mon_client *monc) +{ + monc->hunt_mult /= 2; /* reduce by 50% */ + if (monc->hunt_mult < 1) + monc->hunt_mult = 1; + dout("%s hunt_mult now %d\n", __func__, monc->hunt_mult); +} + /* * Reschedule delayed work timer. */ @@ -963,6 +971,7 @@ static void delayed_work(struct work_struct *work) if (!monc->hunting) { ceph_con_keepalive(&monc->con); __validate_auth(monc); + un_backoff(monc); } if (is_auth && @@ -1123,9 +1132,8 @@ static void finish_hunting(struct ceph_mon_client *monc) dout("%s found mon%d\n", __func__, monc->cur_mon); monc->hunting = false; monc->had_a_connection = true; - monc->hunt_mult /= 2; /* reduce by 50% */ - if (monc->hunt_mult < 1) - monc->hunt_mult = 1; + un_backoff(monc); + __schedule_delayed(monc); } } diff --git a/net/compat.c b/net/compat.c index 5ae7437d3853..7242cce5631b 100644 --- a/net/compat.c +++ b/net/compat.c @@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, optname == SO_ATTACH_REUSEPORT_CBPF) return do_set_attach_filter(sock, level, optname, optval, optlen); - if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + if (!COMPAT_USE_64BIT_TIME && + (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) return do_set_sock_timeout(sock, level, optname, optval, optlen); return sock_setsockopt(sock, level, optname, optval, optlen); @@ -448,7 +449,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname, static int compat_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { - if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + if (!COMPAT_USE_64BIT_TIME && + (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) return do_get_sock_timeout(sock, level, optname, optval, optlen); return sock_getsockopt(sock, level, optname, optval, optlen); } diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index e3e6a3e2ca22..d884d8f5f0e5 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -839,7 +839,7 @@ void dev_mc_flush(struct net_device *dev) EXPORT_SYMBOL(dev_mc_flush); /** - * dev_mc_flush - Init multicast address list + * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 03416e6dd5d7..ba02f0dfe85c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1032,6 +1032,11 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, info_size = sizeof(info); if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; + /* Since malicious users may modify the original data, + * we need to check whether FLOW_RSS is still requested. + */ + if (!(info.flow_type & FLOW_RSS)) + return -EINVAL; } if (info.cmd == ETHTOOL_GRXCLSRLALL) { diff --git a/net/core/filter.c b/net/core/filter.c index d31aff93270d..e77c30ca491d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3240,6 +3240,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; + memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 92d016e87816..385f153fe031 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val) DCCPF_SEQ_WMAX)); } +static void dccp_tasklet_schedule(struct sock *sk) +{ + struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet; + + if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + sock_hold(sk); + __tasklet_schedule(t); + } +} + static void ccid2_hc_tx_rto_expire(struct timer_list *t) { struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer); @@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t) /* if we were blocked before, we may now send cwnd=1 packet */ if (sender_was_blocked) - tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_tasklet_schedule(sk); /* restart backed-off timer */ sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); out: @@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) done: /* check if incoming Acks allow pending packets to be sent */ if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) - tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_tasklet_schedule(sk); dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index b50a8732ff43..1501a20a94ca 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -232,6 +232,7 @@ static void dccp_write_xmitlet(unsigned long data) else dccp_write_xmit(sk); bh_unlock_sock(sk); + sock_put(sk); } static void dccp_write_xmit_timer(struct timer_list *t) @@ -240,7 +241,6 @@ static void dccp_write_xmit_timer(struct timer_list *t) struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; dccp_write_xmitlet((unsigned long)sk); - sock_put(sk); } void dccp_init_xmit_timers(struct sock *sk) diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index b8d95cb71c25..44a7e16bf3b5 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -20,8 +20,8 @@ typedef unsigned __bitwise lowpan_rx_result; struct frag_lowpan_compare_key { u16 tag; u16 d_size; - const struct ieee802154_addr src; - const struct ieee802154_addr dst; + struct ieee802154_addr src; + struct ieee802154_addr dst; }; /* Equivalent of ipv4 struct ipq diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 1790b65944b3..2cc224106b69 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -75,14 +75,14 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb, { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); - struct frag_lowpan_compare_key key = { - .tag = cb->d_tag, - .d_size = cb->d_size, - .src = *src, - .dst = *dst, - }; + struct frag_lowpan_compare_key key = {}; struct inet_frag_queue *q; + key.tag = cb->d_tag; + key.d_size = cb->d_size; + key.src = *src; + key.dst = *dst; + q = inet_frag_find(&ieee802154_lowpan->frags, &key); if (!q) return NULL; @@ -372,7 +372,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); - struct ieee802154_hdr hdr; + struct ieee802154_hdr hdr = {}; int err; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) diff --git a/net/ife/ife.c b/net/ife/ife.c index 7d1ec76e7f43..13bbf8cb6a39 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) int total_pull; u16 ifehdrln; + if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN)) + return NULL; + ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len); ifehdrln = ntohs(ifehdr->metalen); total_pull = skb->dev->hard_header_len + ifehdrln; @@ -92,12 +95,43 @@ struct meta_tlvhdr { __be16 len; }; +static bool __ife_tlv_meta_valid(const unsigned char *skbdata, + const unsigned char *ifehdr_end) +{ + const struct meta_tlvhdr *tlv; + u16 tlvlen; + + if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end)) + return false; + + tlv = (const struct meta_tlvhdr *)skbdata; + tlvlen = ntohs(tlv->len); + + /* tlv length field is inc header, check on minimum */ + if (tlvlen < NLA_HDRLEN) + return false; + + /* overflow by NLA_ALIGN check */ + if (NLA_ALIGN(tlvlen) < tlvlen) + return false; + + if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end)) + return false; + + return true; +} + /* Caller takes care of presenting data in network order */ -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen) { - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + struct meta_tlvhdr *tlv; + + if (!__ife_tlv_meta_valid(skbdata, ifehdr_end)) + return NULL; + tlv = (struct meta_tlvhdr *)skbdata; *dlen = ntohs(tlv->len) - NLA_HDRLEN; *attrtype = ntohs(tlv->type); diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 7523ddb2566b..0e5edd0c7926 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -28,10 +28,9 @@ obj-$(CONFIG_NF_REJECT_IPV4) += nf_reject_ipv4.o obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o -nf_nat_snmp_basic-y := nf_nat_snmp_basic-asn1.o nf_nat_snmp_basic_main.o -$(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic-asn1.h +nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o +$(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o -clean-files := nf_nat_snmp_basic-asn1.c nf_nat_snmp_basic-asn1.h obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index b6e277093e7e..ac110c1d55b5 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -54,7 +54,7 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <linux/netfilter/nf_conntrack_snmp.h> -#include "nf_nat_snmp_basic-asn1.h" +#include "nf_nat_snmp_basic.asn1.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ccb25d80f679..29268efad247 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -709,7 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; - fnhe->fnhe_expires = expires; + fnhe->fnhe_expires = max(1UL, expires); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception @@ -1297,6 +1297,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions); @@ -1310,8 +1340,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (fnhe->fnhe_daddr == daddr) + if (fnhe->fnhe_daddr == daddr) { + if (fnhe->fnhe_expires && + time_after(jiffies, fnhe->fnhe_expires)) { + ip_del_fnhe(nh, daddr); + break; + } return fnhe; + } } return NULL; } @@ -1339,6 +1375,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; + fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } @@ -1636,36 +1673,6 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } -static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) -{ - struct fnhe_hash_bucket *hash; - struct fib_nh_exception *fnhe, __rcu **fnhe_p; - u32 hval = fnhe_hashfun(daddr); - - spin_lock_bh(&fnhe_lock); - - hash = rcu_dereference_protected(nh->nh_exceptions, - lockdep_is_held(&fnhe_lock)); - hash += hval; - - fnhe_p = &hash->chain; - fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); - while (fnhe) { - if (fnhe->fnhe_daddr == daddr) { - rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( - fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); - fnhe_flush_routes(fnhe); - kfree_rcu(fnhe, rcu); - break; - } - fnhe_p = &fnhe->fnhe_next; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, - lockdep_is_held(&fnhe_lock)); - } - - spin_unlock_bh(&fnhe_lock); -} - /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1719,20 +1726,10 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) { + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(&FIB_RES_NH(*res), daddr); - fnhe = NULL; - } else { - goto rt_cache; - } - } - - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - -rt_cache: + else + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2216,39 +2213,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res, * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ - fi = NULL; + do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; - if (do_cache) { + if (fi) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); + if (!do_cache) + goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; - rth = rcu_dereference(*prth); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(nh, fl4->daddr); - fnhe = NULL; - } else { - goto rt_cache; + } else { + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } - - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; - } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); - -rt_cache: if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9ce1c726185e..c9d00ef54dec 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -697,7 +697,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, { return skb->len < size_goal && sock_net(sk)->ipv4.sysctl_tcp_autocorking && - skb != tcp_write_queue_head(sk) && + !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } @@ -1204,7 +1204,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) uarg->zerocopy = 0; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; @@ -2673,7 +2674,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; - else if (val < TCP_QUEUES_NR) + else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 158d105e76da..58e2f479ffb4 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -806,7 +806,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } } } - bbr->idle_restart = 0; + /* Restart after idle ends only once we process a new S/ACK for data */ + if (rs->delivered > 0) + bbr->idle_restart = 0; } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 367def6ddeda..e51c644484dc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 24b5c59b1c53..c2a292dfd137 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 6794ddf0547c..11e4e80cf7e9 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -34,16 +34,15 @@ config IPV6_ROUTE_INFO bool "IPv6: Route Information (RFC 4191) support" depends on IPV6_ROUTER_PREF ---help--- - This is experimental support of Route Information. + Support of Route Information. If unsure, say N. config IPV6_OPTIMISTIC_DAD bool "IPv6: Enable RFC 4429 Optimistic DAD" ---help--- - This is experimental support for optimistic Duplicate - Address Detection. It allows for autoconfigured addresses - to be used more quickly. + Support for optimistic Duplicate Address Detection. It allows for + autoconfigured addresses to be used more quickly. If unsure, say N. @@ -280,7 +279,7 @@ config IPV6_MROUTE depends on IPV6 select IP_MROUTE_COMMON ---help--- - Experimental support for IPv6 multicast forwarding. + Support for IPv6 multicast forwarding. If unsure, say N. config IPV6_MROUTE_MULTIPLE_TABLES diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index c214ffec02f0..ca957dd93a29 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -669,7 +669,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) else mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); - dev->mtu = max_t(int, mtu, IPV6_MIN_MTU); + dev->mtu = max_t(int, mtu, IPV4_MIN_MTU); } /** @@ -881,7 +881,7 @@ static void vti6_dev_setup(struct net_device *dev) dev->priv_destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; - dev->min_mtu = IPV6_MIN_MTU; + dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ccbfa83e4bb0..ce77bcc2490c 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -48,6 +48,34 @@ config NFT_CHAIN_ROUTE_IPV6 fields such as the source, destination, flowlabel, hop-limit and the packet mark. +if NF_NAT_IPV6 + +config NFT_CHAIN_NAT_IPV6 + tristate "IPv6 nf_tables nat chain support" + help + This option enables the "nat" chain for IPv6 in nf_tables. This + chain type is used to perform Network Address Translation (NAT) + packet transformations such as the source, destination address and + source and destination ports. + +config NFT_MASQ_IPV6 + tristate "IPv6 masquerade support for nf_tables" + depends on NFT_MASQ + select NF_NAT_MASQUERADE_IPV6 + help + This is the expression that provides IPv4 masquerading support for + nf_tables. + +config NFT_REDIR_IPV6 + tristate "IPv6 redirect support for nf_tables" + depends on NFT_REDIR + select NF_NAT_REDIRECT + help + This is the expression that provides IPv4 redirect support for + nf_tables. + +endif # NF_NAT_IPV6 + config NFT_REJECT_IPV6 select NF_REJECT_IPV6 default NFT_REJECT @@ -107,39 +135,12 @@ config NF_NAT_IPV6 if NF_NAT_IPV6 -config NFT_CHAIN_NAT_IPV6 - depends on NF_TABLES_IPV6 - tristate "IPv6 nf_tables nat chain support" - help - This option enables the "nat" chain for IPv6 in nf_tables. This - chain type is used to perform Network Address Translation (NAT) - packet transformations such as the source, destination address and - source and destination ports. - config NF_NAT_MASQUERADE_IPV6 tristate "IPv6 masquerade support" help This is the kernel functionality to provide NAT in the masquerade flavour (automatic source address selection) for IPv6. -config NFT_MASQ_IPV6 - tristate "IPv6 masquerade support for nf_tables" - depends on NF_TABLES_IPV6 - depends on NFT_MASQ - select NF_NAT_MASQUERADE_IPV6 - help - This is the expression that provides IPv4 masquerading support for - nf_tables. - -config NFT_REDIR_IPV6 - tristate "IPv6 redirect support for nf_tables" - depends on NF_TABLES_IPV6 - depends on NFT_REDIR - select NF_NAT_REDIRECT - help - This is the expression that provides IPv4 redirect support for - nf_tables. - endif # NF_NAT_IPV6 config IP6_NF_IPTABLES diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 49b954d6d0fa..f4d61736c41a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1835,11 +1835,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb, const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; + struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; - icmph = icmp6_hdr(skb); + icmph = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_icmph), &_icmph); + if (!icmph) + goto out; + if (icmph->icmp6_type != ICMPV6_DEST_UNREACH && icmph->icmp6_type != ICMPV6_PKT_TOOBIG && icmph->icmp6_type != ICMPV6_TIME_EXCEED && @@ -3975,6 +3980,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, @@ -3986,6 +3992,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index f343e6f0fc95..5fe139484919 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4ec76a87aeb8..ea0730028e5d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -148,9 +148,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f85f0d7480ac..4a46df8441c9 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -341,6 +341,9 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_flush_gc(); + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 7e2e7188e7f4..e62e52e8f141 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -437,6 +437,24 @@ static int verify_address_len(const void *p) return 0; } +static inline int sadb_key_len(const struct sadb_key *key) +{ + int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8); + + return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes, + sizeof(uint64_t)); +} + +static int verify_key_len(const void *p) +{ + const struct sadb_key *key = p; + + if (sadb_key_len(key) > key->sadb_key_len) + return -EINVAL; + + return 0; +} + static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx) { return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) + @@ -533,16 +551,25 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void * return -EINVAL; if (ext_hdrs[ext_type-1] != NULL) return -EINVAL; - if (ext_type == SADB_EXT_ADDRESS_SRC || - ext_type == SADB_EXT_ADDRESS_DST || - ext_type == SADB_EXT_ADDRESS_PROXY || - ext_type == SADB_X_EXT_NAT_T_OA) { + switch (ext_type) { + case SADB_EXT_ADDRESS_SRC: + case SADB_EXT_ADDRESS_DST: + case SADB_EXT_ADDRESS_PROXY: + case SADB_X_EXT_NAT_T_OA: if (verify_address_len(p)) return -EINVAL; - } - if (ext_type == SADB_X_EXT_SEC_CTX) { + break; + case SADB_X_EXT_SEC_CTX: if (verify_sec_ctx_len(p)) return -EINVAL; + break; + case SADB_EXT_KEY_AUTH: + case SADB_EXT_KEY_ENCRYPT: + if (verify_key_len(p)) + return -EINVAL; + break; + default: + break; } ext_hdrs[ext_type-1] = (void *) p; } @@ -1104,14 +1131,12 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && - ((key->sadb_key_bits+7) / 8 == 0 || - (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t))) + key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key != NULL && sa->sadb_sa_encrypt != SADB_EALG_NULL && - ((key->sadb_key_bits+7) / 8 == 0 || - (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t))) + key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); x = xfrm_state_alloc(net); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b8f9d45bfeb1..7f1e842ef05a 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -106,8 +106,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) return; /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */ - if (pd->tunnel) + if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); + pd->tunnel = NULL; + pd->session = NULL; + } } static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 7d0c963680e6..1fd9e145076a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6)) + goto end; + if (sp->sa_protocol != PX_PROTO_OL2TP) goto end; @@ -1618,8 +1625,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) return; /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */ - if (pd->tunnel) + if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); + pd->tunnel = NULL; + pd->session = NULL; + } } static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 01dcc0823d1f..1beeea9549fa 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -199,9 +199,19 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - if (!sock_flag(sk, SOCK_ZAPPED)) + if (!sock_flag(sk, SOCK_ZAPPED)) { + struct llc_sap *sap = llc->sap; + + /* Hold this for release_sock(), so that llc_backlog_rcv() + * could still use it. + */ + llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); - release_sock(sk); + release_sock(sk); + llc_sap_put(sap); + } else { + release_sock(sk); + } if (llc->dev) dev_put(llc->dev); sock_put(sk); @@ -920,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (size > llc->dev->mtu) size = llc->dev->mtu; copied = size - hdrlen; + rc = -EINVAL; + if (copied < 0) + goto release; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 163121192aca..4d78375f9872 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { - struct llc_sock *llc = llc_sk(sk); - - del_timer(&llc->pf_cycle_timer.timer); - del_timer(&llc->ack_timer.timer); - del_timer(&llc->rej_sent_timer.timer); - del_timer(&llc->busy_state_timer.timer); - llc->ack_must_be_send = 0; - llc->ack_pf = 0; + llc_sk_stop_all_timers(sk, false); return 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 110e32bcb399..c0ac522b48a1 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -961,6 +961,26 @@ out: return sk; } +void llc_sk_stop_all_timers(struct sock *sk, bool sync) +{ + struct llc_sock *llc = llc_sk(sk); + + if (sync) { + del_timer_sync(&llc->pf_cycle_timer.timer); + del_timer_sync(&llc->ack_timer.timer); + del_timer_sync(&llc->rej_sent_timer.timer); + del_timer_sync(&llc->busy_state_timer.timer); + } else { + del_timer(&llc->pf_cycle_timer.timer); + del_timer(&llc->ack_timer.timer); + del_timer(&llc->rej_sent_timer.timer); + del_timer(&llc->busy_state_timer.timer); + } + + llc->ack_must_be_send = 0; + llc->ack_pf = 0; +} + /** * llc_sk_free - Frees a LLC socket * @sk - socket to free @@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk) llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ - llc_conn_ac_stop_all_timers(sk, NULL); + llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 704b3832dbad..44d8a55e9721 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -594,6 +594,7 @@ config NFT_QUOTA config NFT_REJECT default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" + depends on !NF_TABLES_INET || (IPV6!=m || m) help This option adds the "reject" expression that you can use to explicitly deny and notify via TCP reset/ICMP informational errors diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5ebde4b15810..f36098887ad0 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2384,11 +2384,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) strlcpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)); cfg.syncid = dm->syncid; - rtnl_lock(); - mutex_lock(&ipvs->sync_mutex); ret = start_sync_thread(ipvs, &cfg, dm->state); - mutex_unlock(&ipvs->sync_mutex); - rtnl_unlock(); } else { mutex_lock(&ipvs->sync_mutex); ret = stop_sync_thread(ipvs, dm->state); @@ -3481,12 +3477,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) if (ipvs->mixed_address_family_dests > 0) return -EINVAL; - rtnl_lock(); - mutex_lock(&ipvs->sync_mutex); ret = start_sync_thread(ipvs, &c, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); - mutex_unlock(&ipvs->sync_mutex); - rtnl_unlock(); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index fbaf3bd05b2e..001501e25625 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -49,6 +49,7 @@ #include <linux/kthread.h> #include <linux/wait.h> #include <linux/kernel.h> +#include <linux/sched/signal.h> #include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */ @@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val) /* * Specifiy default interface for outgoing multicasts */ -static int set_mcast_if(struct sock *sk, char *ifname) +static int set_mcast_if(struct sock *sk, struct net_device *dev) { - struct net_device *dev; struct inet_sock *inet = inet_sk(sk); - struct net *net = sock_net(sk); - - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname) * in the in_addr structure passed in as a parameter. */ static int -join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) +join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev) { - struct net *net = sock_net(sk); struct ip_mreqn mreq; - struct net_device *dev; int ret; memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) #ifdef CONFIG_IP_VS_IPV6 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, - char *ifname) + struct net_device *dev) { - struct net *net = sock_net(sk); - struct net_device *dev; int ret; - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, } #endif -static int bind_mcastif_addr(struct socket *sock, char *ifname) +static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) { - struct net *net = sock_net(sock->sk); - struct net_device *dev; __be32 addr; struct sockaddr_in sin; - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; - addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); if (!addr) pr_err("You probably need to specify IP address on " "multicast interface.\n"); IP_VS_DBG(7, "binding socket with (%s) %pI4\n", - ifname, &addr); + dev->name, &addr); /* Now bind the socket with the address of multicast interface */ sin.sin_family = AF_INET; @@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, /* * Set up sending multicast socket over UDP */ -static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) +static int make_send_sock(struct netns_ipvs *ipvs, int id, + struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); - return ERR_PTR(result); + goto error; } - result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn); + *sock_ret = sock; + result = set_mcast_if(sock->sk, dev); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; @@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) set_sock_size(sock->sk, 1, result); if (AF_INET == ipvs->mcfg.mcast_af) - result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn); + result = bind_mcastif_addr(sock, dev); else result = 0; if (result < 0) { @@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) goto error; } - return sock; + return 0; error: - sock_release(sock); - return ERR_PTR(result); + return result; } /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, - int ifindex) +static int make_receive_sock(struct netns_ipvs *ipvs, int id, + struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); - return ERR_PTR(result); + goto error; } + *sock_ret = sock; /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); @@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); - sock->sk->sk_bound_dev_if = ifindex; + sock->sk->sk_bound_dev_if = dev->ifindex; result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); @@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, #ifdef CONFIG_IP_VS_IPV6 if (ipvs->bcfg.mcast_af == AF_INET6) result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr, - ipvs->bcfg.mcast_ifn); + dev); else #endif result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr, - ipvs->bcfg.mcast_ifn); + dev); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; } - return sock; + return 0; error: - sock_release(sock); - return ERR_PTR(result); + return result; } @@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data) int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { - struct ip_vs_sync_thread_data *tinfo; + struct ip_vs_sync_thread_data *tinfo = NULL; struct task_struct **array = NULL, *task; - struct socket *sock; struct net_device *dev; char *name; int (*threadfn)(void *data); - int id, count, hlen; + int id = 0, count, hlen; int result = -ENOMEM; u16 mtu, min_mtu; @@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + /* Do not hold one mutex and then to block on another */ + for (;;) { + rtnl_lock(); + if (mutex_trylock(&ipvs->sync_mutex)) + break; + rtnl_unlock(); + mutex_lock(&ipvs->sync_mutex); + if (rtnl_trylock()) + break; + mutex_unlock(&ipvs->sync_mutex); + } + if (!ipvs->sync_state) { count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX); ipvs->threads_mask = count - 1; @@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); - return -ENODEV; + result = -ENODEV; + goto out_early; } hlen = (AF_INET6 == c->mcast_af) ? sizeof(struct ipv6hdr) + sizeof(struct udphdr) : @@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, c->sync_maxlen = mtu - hlen; if (state == IP_VS_STATE_MASTER) { + result = -EEXIST; if (ipvs->ms) - return -EEXIST; + goto out_early; ipvs->mcfg = *c; name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; } else if (state == IP_VS_STATE_BACKUP) { + result = -EEXIST; if (ipvs->backup_threads) - return -EEXIST; + goto out_early; ipvs->bcfg = *c; name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; } else { - return -EINVAL; + result = -EINVAL; + goto out_early; } if (state == IP_VS_STATE_MASTER) { struct ipvs_master_sync_state *ms; + result = -ENOMEM; ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL); if (!ipvs->ms) goto out; @@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, } else { array = kcalloc(count, sizeof(struct task_struct *), GFP_KERNEL); + result = -ENOMEM; if (!array) goto out; } - tinfo = NULL; for (id = 0; id < count; id++) { - if (state == IP_VS_STATE_MASTER) - sock = make_send_sock(ipvs, id); - else - sock = make_receive_sock(ipvs, id, dev->ifindex); - if (IS_ERR(sock)) { - result = PTR_ERR(sock); - goto outtinfo; - } + result = -ENOMEM; tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) - goto outsocket; + goto out; tinfo->ipvs = ipvs; - tinfo->sock = sock; + tinfo->sock = NULL; if (state == IP_VS_STATE_BACKUP) { tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, GFP_KERNEL); if (!tinfo->buf) - goto outtinfo; + goto out; } else { tinfo->buf = NULL; } tinfo->id = id; + if (state == IP_VS_STATE_MASTER) + result = make_send_sock(ipvs, id, dev, &tinfo->sock); + else + result = make_receive_sock(ipvs, id, dev, &tinfo->sock); + if (result < 0) + goto out; task = kthread_run(threadfn, tinfo, name, ipvs->gen, id); if (IS_ERR(task)) { result = PTR_ERR(task); - goto outtinfo; + goto out; } tinfo = NULL; if (state == IP_VS_STATE_MASTER) @@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, ipvs->sync_state |= state; spin_unlock_bh(&ipvs->sync_buff_lock); + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); + /* increase the module use count */ ip_vs_use_count_inc(); return 0; -outsocket: - sock_release(sock); - -outtinfo: - if (tinfo) { - sock_release(tinfo->sock); - kfree(tinfo->buf); - kfree(tinfo); - } +out: + /* We do not need RTNL lock anymore, release it here so that + * sock_release below and in the kthreads can use rtnl_lock + * to leave the mcast group. + */ + rtnl_unlock(); count = id; while (count-- > 0) { if (state == IP_VS_STATE_MASTER) @@ -1932,13 +1927,23 @@ outtinfo: else kthread_stop(array[count]); } - kfree(array); - -out: if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { kfree(ipvs->ms); ipvs->ms = NULL; } + mutex_unlock(&ipvs->sync_mutex); + if (tinfo) { + if (tinfo->sock) + sock_release(tinfo->sock); + kfree(tinfo->buf); + kfree(tinfo); + } + kfree(array); + return result; + +out_early: + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); return result; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 8ef21d9f9a00..4b2b3d53acfc 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && a->class == b->class && + return a->master == b->master && nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && @@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (expect_matches(i, expect)) { + if (i->class != expect->class) + return -EALREADY; + if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 9fe0ddc333fb..277bbfe26478 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -9,6 +9,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> +#include <linux/kmemleak.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/rcupdate.h> @@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) rcu_read_unlock(); alloc = max(newlen, NF_CT_EXT_PREALLOC); + kmemleak_not_leak(old); new = __krealloc(old, alloc, gfp); if (!new) return NULL; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 4dbb5bad4363..908e51e2dc2b 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, datalen, rtp_exp, rtcp_exp, mediaoff, medialen, daddr); else { - if (nf_ct_expect_related(rtp_exp) == 0) { - if (nf_ct_expect_related(rtcp_exp) != 0) - nf_ct_unexpect_related(rtp_exp); - else + /* -EALREADY handling works around end-points that send + * SDP messages with identical port but different media type, + * we pretend expectation was set up. + */ + int errp = nf_ct_expect_related(rtp_exp); + + if (errp == 0 || errp == -EALREADY) { + int errcp = nf_ct_expect_related(rtcp_exp); + + if (errcp == 0 || errcp == -EALREADY) ret = NF_ACCEPT; + else if (errp == 0) + nf_ct_unexpect_related(rtp_exp); } } nf_ct_expect_put(rtcp_exp); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9134cc429ad4..04d4e3772584 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2361,41 +2361,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (nft_is_active_next(net, old_rule)) { - trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, - old_rule); - if (trans == NULL) { - err = -ENOMEM; - goto err2; - } - nft_deactivate_next(net, old_rule); - chain->use--; - list_add_tail_rcu(&rule->list, &old_rule->list); - } else { + if (!nft_is_active_next(net, old_rule)) { err = -ENOENT; goto err2; } - } else if (nlh->nlmsg_flags & NLM_F_APPEND) - if (old_rule) - list_add_rcu(&rule->list, &old_rule->list); - else - list_add_tail_rcu(&rule->list, &chain->rules); - else { - if (old_rule) - list_add_tail_rcu(&rule->list, &old_rule->list); - else - list_add_rcu(&rule->list, &chain->rules); - } + trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, + old_rule); + if (trans == NULL) { + err = -ENOMEM; + goto err2; + } + nft_deactivate_next(net, old_rule); + chain->use--; - if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { - err = -ENOMEM; - goto err3; + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + list_add_tail_rcu(&rule->list, &old_rule->list); + } else { + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + if (nlh->nlmsg_flags & NLM_F_APPEND) { + if (old_rule) + list_add_rcu(&rule->list, &old_rule->list); + else + list_add_tail_rcu(&rule->list, &chain->rules); + } else { + if (old_rule) + list_add_tail_rcu(&rule->list, &old_rule->list); + else + list_add_rcu(&rule->list, &chain->rules); + } } chain->use++; return 0; -err3: - list_del_rcu(&rule->list); err2: nf_tables_rule_destroy(&ctx, rule); err1: @@ -3207,18 +3212,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = ops->init(set, &desc, nla); if (err < 0) - goto err2; + goto err3; err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err3; + goto err4; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err3: +err4: ops->destroy(set); +err3: + kfree(set->name); err2: kvfree(set); err1: @@ -5738,7 +5745,7 @@ static void nft_chain_commit_update(struct nft_trans *trans) struct nft_base_chain *basechain; if (nft_trans_chain_name(trans)) - strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans)); + swap(trans->ctx.chain->name, nft_trans_chain_name(trans)); if (!nft_is_base_chain(trans->ctx.chain)) return; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 773da82190dc..94df000abb92 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark"); MODULE_ALIAS("ip6t_connmark"); static unsigned int -connmark_tg_shift(struct sk_buff *skb, - const struct xt_connmark_tginfo1 *info, - u8 shift_bits, u8 shift_dir) +connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) { enum ip_conntrack_info ctinfo; + u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; @@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb, switch (info->mode) { case XT_CONNMARK_SET: newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + if (info->shift_dir == D_SHIFT_RIGHT) + newmark >>= info->shift_bits; else - newmark <<= shift_bits; + newmark <<= info->shift_bits; + if (ct->mark != newmark) { ct->mark = newmark; nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_SAVE: - newmark = (ct->mark & ~info->ctmask) ^ - (skb->mark & info->nfmask); - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + new_targetmark = (skb->mark & info->nfmask); + if (info->shift_dir == D_SHIFT_RIGHT) + new_targetmark >>= info->shift_bits; else - newmark <<= shift_bits; + new_targetmark <<= info->shift_bits; + + newmark = (ct->mark & ~info->ctmask) ^ + new_targetmark; if (ct->mark != newmark) { ct->mark = newmark; nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - newmark = (skb->mark & ~info->nfmask) ^ - (ct->mark & info->ctmask); - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + new_targetmark = (ct->mark & info->ctmask); + if (info->shift_dir == D_SHIFT_RIGHT) + new_targetmark >>= info->shift_bits; else - newmark <<= shift_bits; + new_targetmark <<= info->shift_bits; + + newmark = (skb->mark & ~info->nfmask) ^ + new_targetmark; skb->mark = newmark; break; } @@ -89,8 +93,14 @@ static unsigned int connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo1 *info = par->targinfo; - - return connmark_tg_shift(skb, info, 0, 0); + const struct xt_connmark_tginfo2 info2 = { + .ctmark = info->ctmark, + .ctmask = info->ctmask, + .nfmask = info->nfmask, + .mode = info->mode, + }; + + return connmark_tg_shift(skb, &info2); } static unsigned int @@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo2 *info = par->targinfo; - return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info, - info->shift_bits, info->shift_dir); + return connmark_tg_shift(skb, info); } static int connmark_tg_check(const struct xt_tgchk_param *par) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 55342c4d5cec..2e2dd88fc79f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2606,13 +2606,13 @@ static int netlink_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, - "sk Eth Pid Groups " - "Rmem Wmem Dump Locks Drops Inode\n"); + "sk Eth Pid Groups " + "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n", + seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8d %-8lu\n", s, s->sk_protocol, nlk->portid, diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index d7da99a0b0b8..9696ef96b719 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -57,6 +57,8 @@ int nsh_pop(struct sk_buff *skb) return -ENOMEM; nh = (struct nshhdr *)(skb->data); length = nsh_hdr_len(nh); + if (length < NSH_BASE_HDR_LEN) + return -EINVAL; inner_proto = tun_p_to_eth_p(nh->np); if (!pskb_may_pull(skb, length)) return -ENOMEM; @@ -90,6 +92,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) goto out; nsh_len = nsh_hdr_len(nsh_hdr(skb)); + if (nsh_len < NSH_BASE_HDR_LEN) + goto out; if (unlikely(!pskb_may_pull(skb, nsh_len))) goto out; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7322aa1e382e..492ab0c36f7c 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1712,13 +1712,10 @@ static void nlattr_set(struct nlattr *attr, u8 val, /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { - if (tbl[nla_type(nla)].next) - tbl = tbl[nla_type(nla)].next; - nlattr_set(nla, val, tbl); - } else { + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl); + else memset(nla_data(nla), val, nla_len(nla)); - } if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c31b0687396a..01f3515cada0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) skb_set_queue_mapping(skb, queue_index); } -/* register_prot_hook must be invoked with the po->bind_lock held, +/* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ -static void register_prot_hook(struct sock *sk) +static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); @@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk) } } -/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock - * held. If the sync parameter is true, we will temporarily drop +static void register_prot_hook(struct sock *sk) +{ + lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); + __register_prot_hook(sk); +} + +/* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the @@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); + lockdep_assert_held_once(&po->bind_lock); + po->running = 0; if (po->fanout) @@ -3252,7 +3259,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, if (proto) { po->prot_hook.type = proto; - register_prot_hook(sk); + __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); @@ -3732,12 +3739,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_loss = !!val; - return 0; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_loss = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_AUXDATA: { @@ -3748,7 +3761,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->auxdata = !!val; + release_sock(sk); return 0; } case PACKET_ORIGDEV: @@ -3760,7 +3775,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->origdev = !!val; + release_sock(sk); return 0; } case PACKET_VNET_HDR: @@ -3769,15 +3786,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (sock->type != SOCK_RAW) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->has_vnet_hdr = !!val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->has_vnet_hdr = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_TIMESTAMP: { @@ -3815,11 +3837,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_tx_has_off = !!val; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_tx_has_off = !!val; + ret = 0; + } + release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: diff --git a/net/packet/internal.h b/net/packet/internal.h index a1d2b2319ae9..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -112,10 +112,12 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; - unsigned int running:1, /* prot_hook is attached*/ - auxdata:1, + unsigned int running; /* bind_lock must be held */ + unsigned int auxdata:1, /* writer must hold sock lock */ origdev:1, - has_vnet_hdr:1; + has_vnet_hdr:1, + tp_loss:1, + tp_tx_has_off:1; int pressure; int ifindex; /* bound device */ __be16 num; @@ -125,8 +127,6 @@ struct packet_sock { enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; - unsigned int tp_loss:1; - unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index eea1d8611b20..13b38ad0fa4a 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -547,7 +547,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd, ic->i_send_cq, ic->i_recv_cq); - return ret; + goto out; sends_out: vfree(ic->i_sends); @@ -572,6 +572,7 @@ send_cq_out: ic->i_send_cq = NULL; rds_ibdev_out: rds_ib_remove_conn(rds_ibdev, conn); +out: rds_ib_dev_put(rds_ibdev); return ret; diff --git a/net/rds/recv.c b/net/rds/recv.c index de50e2126e40..dc67458b52f0 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, struct rds_cmsg_rx_trace t; int i, j; + memset(&t, 0, sizeof(t)); inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock(); t.rx_traces = rs->rs_rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index a5994cf0512b..8527cfdc446d 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, } } - return 0; + return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, @@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u16 mtype; u16 dlen; - curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); + curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, + &dlen, NULL); + if (!curr_data) { + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); + return TC_ACT_SHOT; + } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a366e4c9413a..4808713c73b9 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f) return f->next == &detached; } +static bool fq_flow_is_throttled(const struct fq_flow *f) +{ + return f->next == &throttled; +} + +static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) +{ + if (head->first) + head->last->next = flow; + else + head->first = flow; + head->last = flow; + flow->next = NULL; +} + +static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) +{ + rb_erase(&f->rate_node, &q->delayed); + q->throttled_flows--; + fq_flow_add_tail(&q->old_flows, f); +} + static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) { struct rb_node **p = &q->delayed.rb_node, *parent = NULL; @@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) static struct kmem_cache *fq_flow_cachep __read_mostly; -static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) -{ - if (head->first) - head->last->next = flow; - else - head->first = flow; - head->last = flow; - flow->next = NULL; -} /* limit number of collected flows per round */ #define FQ_GC_MAX 8 @@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (fq_flow_is_throttled(f)) + fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; } return f; @@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) q->time_next_delayed_flow = f->time_next_packet; break; } - rb_erase(p, &q->delayed); - q->throttled_flows--; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_unset_throttled(q, f); } } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 837806dd5799..a47179da24e6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; - int state; + int first_time = 1; /* is this the first time through the loop */ int error = 0; + int state; /* The association should be held so we should be safe. */ ep = asoc->ep; @@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); + /* If the first chunk in the packet is AUTH, do special + * processing specified in Section 6.3 of SCTP-AUTH spec + */ + if (first_time && subtype.chunk == SCTP_CID_AUTH) { + struct sctp_chunkhdr *next_hdr; + + next_hdr = sctp_inq_peek(inqueue); + if (!next_hdr) + goto normal; + + /* If the next chunk is COOKIE-ECHO, skip the AUTH + * chunk while saving a pointer to it so we can do + * Authentication later (during cookie-echo + * processing). + */ + if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { + chunk->auth_chunk = skb_clone(chunk->skb, + GFP_ATOMIC); + chunk->auth = 1; + continue; + } + } + +normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has @@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; + + if (first_time) + first_time = 0; } sctp_association_put(asoc); } diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 23ebc5318edc..eb93ffe2408b 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -217,7 +217,7 @@ new_skb: skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 2e3f7b75a8ec..42247110d842 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -895,6 +895,9 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1; + if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET) + return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr; + return __sctp_v6_cmp_addr(addr1, addr2); } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5a4fb1dc8400..e62addb60434 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1152,7 +1152,7 @@ struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { - static const char error[] = "Association exceeded its max_retans count"; + static const char error[] = "Association exceeded its max_retrans count"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr); struct sctp_chunk *retval; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index dd0594a10961..c9ae3404b1bb 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk( struct sctp_cmd_seq *commands); static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk); static enum sctp_disposition __sctp_sf_do_9_1_abort( @@ -626,6 +623,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, return SCTP_DISPOSITION_CONSUME; } +static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, + const struct sctp_association *asoc) +{ + struct sctp_chunk auth; + + if (!chunk->auth_chunk) + return true; + + /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo + * is supposed to be authenticated and we have to do delayed + * authentication. We've just recreated the association using + * the information in the cookie and now it's much easier to + * do the authentication. + */ + + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + return false; + + /* set-up our fake chunk so that we can process it */ + auth.skb = chunk->auth_chunk; + auth.asoc = chunk->asoc; + auth.sctp_hdr = chunk->sctp_hdr; + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); + auth.transport = chunk->transport; + + return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR; +} + /* * Respond to a normal COOKIE ECHO chunk. * We are the side that is being asked for an association. @@ -763,37 +792,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, if (error) goto nomem_init; - /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo - * is supposed to be authenticated and we have to do delayed - * authentication. We've just recreated the association using - * the information in the cookie and now it's much easier to - * do the authentication. - */ - if (chunk->auth_chunk) { - struct sctp_chunk auth; - enum sctp_ierror ret; - - /* Make sure that we and the peer are AUTH capable */ - if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - - /* set-up our fake chunk so that we can process it */ - auth.skb = chunk->auth_chunk; - auth.asoc = chunk->asoc; - auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = (struct sctp_chunkhdr *) - skb_push(chunk->auth_chunk, - sizeof(struct sctp_chunkhdr)); - skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); - auth.transport = chunk->transport; - - ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - if (ret != SCTP_IERROR_NO_ERROR) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } repl = sctp_make_cookie_ack(new_asoc, chunk); @@ -1794,13 +1795,18 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( GFP_ATOMIC)) goto nomem; + if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) + goto nomem; + + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Make sure no new addresses are being added during the * restart. Though this is a pretty complicated attack * since you'd have to get inside the cookie. */ - if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { + if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) return SCTP_DISPOSITION_CONSUME; - } /* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes * the peer has restarted (Action A), it MUST NOT setup a new @@ -1906,6 +1912,12 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( GFP_ATOMIC)) goto nomem; + if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) + goto nomem; + + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -2003,6 +2015,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( * a COOKIE ACK. */ + if (!sctp_auth_chunk_verify(net, chunk, asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Don't accidentally move back into established state. */ if (asoc->state < SCTP_STATE_ESTABLISHED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -2050,7 +2065,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( } } - repl = sctp_make_cookie_ack(new_asoc, chunk); + repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; @@ -4165,10 +4180,7 @@ gen_shutdown: * The return value is the disposition of the chunk. */ static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk) { struct sctp_shared_key *sh_key = NULL; @@ -4269,7 +4281,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, commands); auth_hdr = (struct sctp_authhdr *)chunk->skb->data; - error = sctp_sf_authenticate(net, ep, asoc, type, chunk); + error = sctp_sf_authenticate(asoc, chunk); switch (error) { case SCTP_IERROR_AUTH_BAD_HMAC: /* Generate the ERROR chunk and discard the rest diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f799043abec9..f1f1d1b232ba 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -240,6 +240,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) new->out = NULL; new->in = NULL; + new->outcnt = 0; + new->incnt = 0; } static int sctp_send_reconf(struct sctp_association *asoc, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5f8046c62d90..544bab42f925 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -292,6 +292,17 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc) smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC); } +/* register a new rmb */ +static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc) +{ + /* register memory region for new rmb */ + if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) { + rmb_desc->regerr = 1; + return -EFAULT; + } + return 0; +} + static int smc_clnt_conf_first_link(struct smc_sock *smc) { struct smc_link_group *lgr = smc->conn.lgr; @@ -321,9 +332,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) smc_wr_remember_qp_attr(link); - rc = smc_wr_reg_send(link, - smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) + if (smc_reg_rmb(link, smc->conn.rmb_desc)) return SMC_CLC_DECL_INTERR; /* send CONFIRM LINK response over RoCE fabric */ @@ -473,13 +482,8 @@ static int smc_connect_rdma(struct smc_sock *smc) goto decline_rdma_unlock; } } else { - struct smc_buf_desc *buf_desc = smc->conn.rmb_desc; - - if (!buf_desc->reused) { - /* register memory region for new rmb */ - rc = smc_wr_reg_send(link, - buf_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) { + if (!smc->conn.rmb_desc->reused) { + if (smc_reg_rmb(link, smc->conn.rmb_desc)) { reason_code = SMC_CLC_DECL_INTERR; goto decline_rdma_unlock; } @@ -719,9 +723,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) link = &lgr->lnk[SMC_SINGLE_LINK]; - rc = smc_wr_reg_send(link, - smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) + if (smc_reg_rmb(link, smc->conn.rmb_desc)) return SMC_CLC_DECL_INTERR; /* send CONFIRM LINK request to client over the RoCE fabric */ @@ -854,13 +856,8 @@ static void smc_listen_work(struct work_struct *work) smc_rx_init(new_smc); if (local_contact != SMC_FIRST_CONTACT) { - struct smc_buf_desc *buf_desc = new_smc->conn.rmb_desc; - - if (!buf_desc->reused) { - /* register memory region for new rmb */ - rc = smc_wr_reg_send(link, - buf_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) { + if (!new_smc->conn.rmb_desc->reused) { + if (smc_reg_rmb(link, new_smc->conn.rmb_desc)) { reason_code = SMC_CLC_DECL_INTERR; goto decline_rdma_unlock; } @@ -978,10 +975,6 @@ static void smc_tcp_listen_work(struct work_struct *work) } out: - if (lsmc->clcsock) { - sock_release(lsmc->clcsock); - lsmc->clcsock = NULL; - } release_sock(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_listen */ } @@ -1170,13 +1163,15 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, /* delegate to CLC child sock */ release_sock(sk); mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); - /* if non-blocking connect finished ... */ lock_sock(sk); - if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) { - sk->sk_err = smc->clcsock->sk->sk_err; - if (sk->sk_err) { - mask |= EPOLLERR; - } else { + sk->sk_err = smc->clcsock->sk->sk_err; + if (sk->sk_err) { + mask |= EPOLLERR; + } else { + /* if non-blocking connect finished ... */ + if (sk->sk_state == SMC_INIT && + mask & EPOLLOUT && + smc->clcsock->sk->sk_state != TCP_CLOSE) { rc = smc_connect_rdma(smc); if (rc < 0) mask |= EPOLLERR; @@ -1259,14 +1254,12 @@ static int smc_shutdown(struct socket *sock, int how) rc = smc_close_shutdown_write(smc); break; case SHUT_RD: - if (sk->sk_state == SMC_LISTEN) - rc = smc_close_active(smc); - else - rc = 0; - /* nothing more to do because peer is not involved */ + rc = 0; + /* nothing more to do because peer is not involved */ break; } - rc1 = kernel_sock_shutdown(smc->clcsock, how); + if (smc->clcsock) + rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; @@ -1322,8 +1315,11 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, smc = smc_sk(sk); lock_sock(sk); - if (sk->sk_state != SMC_ACTIVE) + if (sk->sk_state != SMC_ACTIVE) { + release_sock(sk); goto out; + } + release_sock(sk); if (smc->use_fallback) rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); @@ -1331,7 +1327,6 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, rc = sock_no_sendpage(sock, page, offset, size, flags); out: - release_sock(sk); return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f44f6803f7ff..d4bd01bb44e1 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -32,6 +32,9 @@ static u32 smc_lgr_num; /* unique link group number */ +static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk, + bool is_rmb); + static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { /* client link group creation always follows the server link group @@ -234,9 +237,22 @@ static void smc_buf_unuse(struct smc_connection *conn) conn->sndbuf_size = 0; } if (conn->rmb_desc) { - conn->rmb_desc->reused = true; - conn->rmb_desc->used = 0; - conn->rmbe_size = 0; + if (!conn->rmb_desc->regerr) { + conn->rmb_desc->reused = 1; + conn->rmb_desc->used = 0; + conn->rmbe_size = 0; + } else { + /* buf registration failed, reuse not possible */ + struct smc_link_group *lgr = conn->lgr; + struct smc_link *lnk; + + write_lock_bh(&lgr->rmbs_lock); + list_del(&conn->rmb_desc->list); + write_unlock_bh(&lgr->rmbs_lock); + + lnk = &lgr->lnk[SMC_SINGLE_LINK]; + smc_buf_free(conn->rmb_desc, lnk, true); + } } } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 07e2a393e6d9..5dfcb15d529f 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -123,7 +123,8 @@ struct smc_buf_desc { */ u32 order; /* allocation order */ u32 used; /* currently used / unused */ - bool reused; /* new created / reused */ + u8 reused : 1; /* new created / reused */ + u8 regerr : 1; /* err during registration */ }; struct smc_rtoken { /* address/key of remote RMB */ diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 805b139756db..092bebc70048 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err) static void strp_start_timer(struct strparser *strp, long timeo) { - if (timeo) + if (timeo && timeo != LONG_MAX) mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 806395687bb6..c2266f387213 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1887,7 +1887,7 @@ call_connect_status(struct rpc_task *task) dprint_status(task); - trace_rpc_connect_status(task, status); + trace_rpc_connect_status(task); task->tk_status = 0; switch (status) { case -ECONNREFUSED: @@ -2014,6 +2014,9 @@ call_transmit_status(struct rpc_task *task) case -EPERM: if (RPC_IS_SOFTCONN(task)) { xprt_end_transmit(task); + if (!task->tk_msg.rpc_proc->p_proc) + trace_xprt_ping(task->tk_xprt, + task->tk_status); rpc_exit(task, task->tk_status); break; } @@ -2112,6 +2115,9 @@ call_status(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; int status; + if (!task->tk_msg.rpc_proc->p_proc) + trace_xprt_ping(task->tk_xprt, task->tk_status); + if (req->rq_reply_bytes_recvd > 0 && !req->rq_bytes_sent) task->tk_status = req->rq_reply_bytes_recvd; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 0f08934b2cea..c81ef5e6c981 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1375,6 +1375,7 @@ rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry) struct dentry *clnt_dir = pipe_dentry->d_parent; struct dentry *gssd_dir = clnt_dir->d_parent; + dget(pipe_dentry); __rpc_rmpipe(d_inode(clnt_dir), pipe_dentry); __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1); __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index d9db2eab3a8d..3fe5d60ab0e2 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,7 +276,7 @@ static void rpc_set_active(struct rpc_task *task) { rpc_task_set_debuginfo(task); set_bit(RPC_TASK_ACTIVE, &task->tk_runstate); - trace_rpc_task_begin(task->tk_client, task, NULL); + trace_rpc_task_begin(task, NULL); } /* @@ -291,7 +291,7 @@ static int rpc_complete_task(struct rpc_task *task) unsigned long flags; int ret; - trace_rpc_task_complete(task->tk_client, task, NULL); + trace_rpc_task_complete(task, NULL); spin_lock_irqsave(&wq->lock, flags); clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); @@ -358,7 +358,7 @@ static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n", task->tk_pid, rpc_qname(q), jiffies); - trace_rpc_task_sleep(task->tk_client, task, q); + trace_rpc_task_sleep(task, q); __rpc_add_wait_queue(q, task, queue_priority); @@ -428,7 +428,7 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq, return; } - trace_rpc_task_wakeup(task->tk_client, task, queue); + trace_rpc_task_wakeup(task, queue); __rpc_remove_wait_queue(queue, task); @@ -780,7 +780,7 @@ static void __rpc_execute(struct rpc_task *task) } if (!do_action) break; - trace_rpc_task_run_action(task->tk_client, task, do_action); + trace_rpc_task_run_action(task, do_action); do_action(task); /* diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 1e671333c3d5..f68aa46c9dd7 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -24,6 +24,8 @@ #include <linux/sunrpc/metrics.h> #include <linux/rcupdate.h> +#include <trace/events/sunrpc.h> + #include "netns.h" #define RPCDBG_FACILITY RPCDBG_MISC @@ -148,7 +150,7 @@ void rpc_count_iostats_metrics(const struct rpc_task *task, struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; - ktime_t delta, now; + ktime_t backlog, execute, now; if (!op_metrics || !req) return; @@ -164,16 +166,20 @@ void rpc_count_iostats_metrics(const struct rpc_task *task, op_metrics->om_bytes_sent += req->rq_xmit_bytes_sent; op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd; + backlog = 0; if (ktime_to_ns(req->rq_xtime)) { - delta = ktime_sub(req->rq_xtime, task->tk_start); - op_metrics->om_queue = ktime_add(op_metrics->om_queue, delta); + backlog = ktime_sub(req->rq_xtime, task->tk_start); + op_metrics->om_queue = ktime_add(op_metrics->om_queue, backlog); } + op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); - delta = ktime_sub(now, task->tk_start); - op_metrics->om_execute = ktime_add(op_metrics->om_execute, delta); + execute = ktime_sub(now, task->tk_start); + op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute); spin_unlock(&op_metrics->om_lock); + + trace_rpc_stats_latency(req->rq_task, backlog, req->rq_rtt, execute); } EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index f2b7cb540e61..09a0315ea77b 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -37,12 +37,6 @@ struct rpc_buffer { char data[]; }; -static inline int rpc_reply_expected(struct rpc_task *task) -{ - return (task->tk_msg.rpc_proc != NULL) && - (task->tk_msg.rpc_proc->p_decode != NULL); -} - static inline int sock_is_loopback(struct sock *sk) { struct dst_entry *dst; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index e34f4ee7f2b6..30afbd236656 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1519,6 +1519,88 @@ out: EXPORT_SYMBOL_GPL(xdr_process_buf); /** + * xdr_stream_decode_opaque - Decode variable length opaque + * @xdr: pointer to xdr_stream + * @ptr: location to store opaque data + * @size: size of storage buffer @ptr + * + * Return values: + * On success, returns size of object stored in *@ptr + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE on overflow of storage buffer @ptr + */ +ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size) +{ + ssize_t ret; + void *p; + + ret = xdr_stream_decode_opaque_inline(xdr, &p, size); + if (ret <= 0) + return ret; + memcpy(ptr, p, ret); + return ret; +} +EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque); + +/** + * xdr_stream_decode_opaque_dup - Decode and duplicate variable length opaque + * @xdr: pointer to xdr_stream + * @ptr: location to store pointer to opaque data + * @maxlen: maximum acceptable object size + * @gfp_flags: GFP mask to use + * + * Return values: + * On success, returns size of object stored in *@ptr + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE if the size of the object would exceed @maxlen + * %-ENOMEM on memory allocation failure + */ +ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr, + size_t maxlen, gfp_t gfp_flags) +{ + ssize_t ret; + void *p; + + ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen); + if (ret > 0) { + *ptr = kmemdup(p, ret, gfp_flags); + if (*ptr != NULL) + return ret; + ret = -ENOMEM; + } + *ptr = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_dup); + +/** + * xdr_stream_decode_string - Decode variable length string + * @xdr: pointer to xdr_stream + * @str: location to store string + * @size: size of storage buffer @str + * + * Return values: + * On success, returns length of NUL-terminated string stored in *@str + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE on overflow of storage buffer @str + */ +ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size) +{ + ssize_t ret; + void *p; + + ret = xdr_stream_decode_opaque_inline(xdr, &p, size); + if (ret > 0) { + memcpy(str, p, ret); + str[ret] = '\0'; + return strlen(str); + } + *str = '\0'; + return ret; +} +EXPORT_SYMBOL_GPL(xdr_stream_decode_string); + +/** * xdr_stream_decode_string_dup - Decode and duplicate variable length string * @xdr: pointer to xdr_stream * @str: location to store pointer to string diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8f0ad4f268da..70f005044f06 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -826,6 +826,7 @@ static void xprt_connect_status(struct rpc_task *task) * @xprt: transport on which the original request was transmitted * @xid: RPC XID of incoming reply * + * Caller holds xprt->recv_lock. */ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) { @@ -834,6 +835,7 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) list_for_each_entry(entry, &xprt->recv, rq_list) if (entry->rq_xid == xid) { trace_xprt_lookup_rqst(xprt, xid, 0); + entry->rq_rtt = ktime_sub(ktime_get(), entry->rq_xtime); return entry; } @@ -889,7 +891,13 @@ __must_hold(&req->rq_xprt->recv_lock) } } -static void xprt_update_rtt(struct rpc_task *task) +/** + * xprt_update_rtt - Update RPC RTT statistics + * @task: RPC request that recently completed + * + * Caller holds xprt->recv_lock. + */ +void xprt_update_rtt(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_rtt *rtt = task->tk_client->cl_rtt; @@ -902,13 +910,14 @@ static void xprt_update_rtt(struct rpc_task *task) rpc_set_timeo(rtt, timer, req->rq_ntrans - 1); } } +EXPORT_SYMBOL_GPL(xprt_update_rtt); /** * xprt_complete_rqst - called when reply processing is complete * @task: RPC request that recently completed * @copied: actual number of bytes received from the transport * - * Caller holds transport lock. + * Caller holds xprt->recv_lock. */ void xprt_complete_rqst(struct rpc_task *task, int copied) { @@ -920,9 +929,6 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) trace_xprt_complete_rqst(xprt, req->rq_xid, copied); xprt->stat.recvs++; - req->rq_rtt = ktime_sub(ktime_get(), req->rq_xtime); - if (xprt->ops->timer != NULL) - xprt_update_rtt(task); list_del_init(&req->rq_list); req->rq_private_buf.len = copied; @@ -1003,7 +1009,7 @@ void xprt_transmit(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; unsigned int connect_cookie; - int status, numreqs; + int status; dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen); @@ -1027,7 +1033,6 @@ void xprt_transmit(struct rpc_task *task) return; connect_cookie = xprt->connect_cookie; - req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); trace_xprt_transmit(xprt, req->rq_xid, status); if (status != 0) { @@ -1042,9 +1047,6 @@ void xprt_transmit(struct rpc_task *task) xprt->ops->set_retrans_timeout(task); - numreqs = atomic_read(&xprt->num_reqs); - if (numreqs > xprt->stat.max_slots) - xprt->stat.max_slots = numreqs; xprt->stat.sends++; xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs; xprt->stat.bklog_u += xprt->backlog.qlen; @@ -1106,14 +1108,15 @@ static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt) { struct rpc_rqst *req = ERR_PTR(-EAGAIN); - if (!atomic_add_unless(&xprt->num_reqs, 1, xprt->max_reqs)) + if (xprt->num_reqs >= xprt->max_reqs) goto out; + ++xprt->num_reqs; spin_unlock(&xprt->reserve_lock); req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS); spin_lock(&xprt->reserve_lock); if (req != NULL) goto out; - atomic_dec(&xprt->num_reqs); + --xprt->num_reqs; req = ERR_PTR(-ENOMEM); out: return req; @@ -1121,7 +1124,8 @@ out: static bool xprt_dynamic_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (atomic_add_unless(&xprt->num_reqs, -1, xprt->min_reqs)) { + if (xprt->num_reqs > xprt->min_reqs) { + --xprt->num_reqs; kfree(req); return true; } @@ -1157,6 +1161,8 @@ void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) spin_unlock(&xprt->reserve_lock); return; out_init_req: + xprt->stat.max_slots = max_t(unsigned int, xprt->stat.max_slots, + xprt->num_reqs); task->tk_status = 0; task->tk_rqstp = req; xprt_request_init(task, xprt); @@ -1224,7 +1230,7 @@ struct rpc_xprt *xprt_alloc(struct net *net, size_t size, else xprt->max_reqs = num_prealloc; xprt->min_reqs = num_prealloc; - atomic_set(&xprt->num_reqs, num_prealloc); + xprt->num_reqs = num_prealloc; return xprt; diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index ed1a4a3065ee..47ebac949769 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -44,13 +44,6 @@ static int rpcrdma_bc_setup_rqst(struct rpcrdma_xprt *r_xprt, if (IS_ERR(req)) return PTR_ERR(req); - rb = rpcrdma_alloc_regbuf(RPCRDMA_HDRBUF_SIZE, - DMA_TO_DEVICE, GFP_KERNEL); - if (IS_ERR(rb)) - goto out_fail; - req->rl_rdmabuf = rb; - xdr_buf_init(&req->rl_hdrbuf, rb->rg_base, rdmab_length(rb)); - size = r_xprt->rx_data.inline_rsize; rb = rpcrdma_alloc_regbuf(size, DMA_TO_DEVICE, GFP_KERNEL); if (IS_ERR(rb)) diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index d5f95bb39300..5cc68a824f45 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -191,7 +191,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mr = rpcrdma_mr_get(r_xprt); if (!mr) - return ERR_PTR(-ENOBUFS); + return ERR_PTR(-EAGAIN); pageoff = offset_in_page(seg1->mr_offset); seg1->mr_offset -= pageoff; /* start of page */ @@ -251,6 +251,16 @@ out_maperr: return ERR_PTR(-EIO); } +/* Post Send WR containing the RPC Call message. + */ +static int +fmr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) +{ + struct ib_send_wr *bad_wr; + + return ib_post_send(ia->ri_id->qp, &req->rl_sendctx->sc_wr, &bad_wr); +} + /* Invalidate all memory regions that were registered for "req". * * Sleeps until it is safe for the host CPU to access the @@ -305,6 +315,7 @@ out_reset: const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, + .ro_send = fmr_op_send, .ro_unmap_sync = fmr_op_unmap_sync, .ro_recover_mr = fmr_op_recover_mr, .ro_open = fmr_op_open, diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 90f688f19783..c5743a0960be 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -357,8 +357,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct rpcrdma_mr *mr; struct ib_mr *ibmr; struct ib_reg_wr *reg_wr; - struct ib_send_wr *bad_wr; - int rc, i, n; + int i, n; u8 key; mr = NULL; @@ -367,7 +366,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, rpcrdma_mr_defer_recovery(mr); mr = rpcrdma_mr_get(r_xprt); if (!mr) - return ERR_PTR(-ENOBUFS); + return ERR_PTR(-EAGAIN); } while (mr->frwr.fr_state != FRWR_IS_INVALID); frwr = &mr->frwr; frwr->fr_state = FRWR_IS_VALID; @@ -407,22 +406,12 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, ib_update_fast_reg_key(ibmr, ++key); reg_wr = &frwr->fr_regwr; - reg_wr->wr.next = NULL; - reg_wr->wr.opcode = IB_WR_REG_MR; - frwr->fr_cqe.done = frwr_wc_fastreg; - reg_wr->wr.wr_cqe = &frwr->fr_cqe; - reg_wr->wr.num_sge = 0; - reg_wr->wr.send_flags = 0; reg_wr->mr = ibmr; reg_wr->key = ibmr->rkey; reg_wr->access = writing ? IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : IB_ACCESS_REMOTE_READ; - rc = ib_post_send(ia->ri_id->qp, ®_wr->wr, &bad_wr); - if (rc) - goto out_senderr; - mr->mr_handle = ibmr->rkey; mr->mr_length = ibmr->length; mr->mr_offset = ibmr->iova; @@ -442,11 +431,40 @@ out_mapmr_err: frwr->fr_mr, n, mr->mr_nents); rpcrdma_mr_defer_recovery(mr); return ERR_PTR(-EIO); +} -out_senderr: - pr_err("rpcrdma: FRWR registration ib_post_send returned %i\n", rc); - rpcrdma_mr_defer_recovery(mr); - return ERR_PTR(-ENOTCONN); +/* Post Send WR containing the RPC Call message. + * + * For FRMR, chain any FastReg WRs to the Send WR. Only a + * single ib_post_send call is needed to register memory + * and then post the Send WR. + */ +static int +frwr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) +{ + struct ib_send_wr *post_wr, *bad_wr; + struct rpcrdma_mr *mr; + + post_wr = &req->rl_sendctx->sc_wr; + list_for_each_entry(mr, &req->rl_registered, mr_list) { + struct rpcrdma_frwr *frwr; + + frwr = &mr->frwr; + + frwr->fr_cqe.done = frwr_wc_fastreg; + frwr->fr_regwr.wr.next = post_wr; + frwr->fr_regwr.wr.wr_cqe = &frwr->fr_cqe; + frwr->fr_regwr.wr.num_sge = 0; + frwr->fr_regwr.wr.opcode = IB_WR_REG_MR; + frwr->fr_regwr.wr.send_flags = 0; + + post_wr = &frwr->fr_regwr.wr; + } + + /* If ib_post_send fails, the next ->send_request for + * @req will queue these MWs for recovery. + */ + return ib_post_send(ia->ri_id->qp, post_wr, &bad_wr); } /* Handle a remotely invalidated mr on the @mrs list @@ -561,6 +579,7 @@ reset_mrs: const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, + .ro_send = frwr_op_send, .ro_reminv = frwr_op_reminv, .ro_unmap_sync = frwr_op_unmap_sync, .ro_recover_mr = frwr_op_recover_mr, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index f0855a959a27..e8adad33d0bb 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -365,7 +365,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, false, &mr); if (IS_ERR(seg)) - return PTR_ERR(seg); + goto out_maperr; rpcrdma_mr_push(mr, &req->rl_registered); if (encode_read_segment(xdr, mr, pos) < 0) @@ -377,6 +377,11 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, } while (nsegs); return 0; + +out_maperr: + if (PTR_ERR(seg) == -EAGAIN) + xprt_wait_for_buffer_space(rqst->rq_task, NULL); + return PTR_ERR(seg); } /* Register and XDR encode the Write list. Supports encoding a list @@ -423,7 +428,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true, &mr); if (IS_ERR(seg)) - return PTR_ERR(seg); + goto out_maperr; rpcrdma_mr_push(mr, &req->rl_registered); if (encode_rdma_segment(xdr, mr) < 0) @@ -440,6 +445,11 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, *segcount = cpu_to_be32(nchunks); return 0; + +out_maperr: + if (PTR_ERR(seg) == -EAGAIN) + xprt_wait_for_buffer_space(rqst->rq_task, NULL); + return PTR_ERR(seg); } /* Register and XDR encode the Reply chunk. Supports encoding an array @@ -481,7 +491,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true, &mr); if (IS_ERR(seg)) - return PTR_ERR(seg); + goto out_maperr; rpcrdma_mr_push(mr, &req->rl_registered); if (encode_rdma_segment(xdr, mr) < 0) @@ -498,6 +508,11 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, *segcount = cpu_to_be32(nchunks); return 0; + +out_maperr: + if (PTR_ERR(seg) == -EAGAIN) + xprt_wait_for_buffer_space(rqst->rq_task, NULL); + return PTR_ERR(seg); } /** @@ -724,8 +739,8 @@ rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, * Returns: * %0 if the RPC was sent successfully, * %-ENOTCONN if the connection was lost, - * %-EAGAIN if not enough pages are available for on-demand reply buffer, - * %-ENOBUFS if no MRs are available to register chunks, + * %-EAGAIN if the caller should call again with the same arguments, + * %-ENOBUFS if the caller should call again after a delay, * %-EMSGSIZE if the transport header is too small, * %-EIO if a permanent problem occurred while marshaling. */ @@ -868,10 +883,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) return 0; out_err: - if (ret != -ENOBUFS) { - pr_err("rpcrdma: header marshaling failed (%d)\n", ret); - r_xprt->rx_stats.failed_marshal_count++; - } + r_xprt->rx_stats.failed_marshal_count++; return ret; } @@ -1366,7 +1378,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) trace_xprtrdma_reply(rqst->rq_task, rep, req, credits); - queue_work_on(req->rl_cpu, rpcrdma_receive_wq, &rep->rr_work); + queue_work(rpcrdma_receive_wq, &rep->rr_work); return; out_badstatus: diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 4b1ecfe979cf..cc1aad325496 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -52,7 +52,6 @@ #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/sunrpc/addr.h> -#include <linux/smp.h> #include "xprt_rdma.h" @@ -237,8 +236,6 @@ rpcrdma_connect_worker(struct work_struct *work) struct rpc_xprt *xprt = &r_xprt->rx_xprt; spin_lock_bh(&xprt->transport_lock); - if (++xprt->connect_cookie == 0) /* maintain a reserved value */ - ++xprt->connect_cookie; if (ep->rep_connected > 0) { if (!xprt_test_and_set_connected(xprt)) xprt_wake_pending_tasks(xprt, 0); @@ -540,29 +537,6 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task) } } -/* Allocate a fixed-size buffer in which to construct and send the - * RPC-over-RDMA header for this request. - */ -static bool -rpcrdma_get_rdmabuf(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - gfp_t flags) -{ - size_t size = RPCRDMA_HDRBUF_SIZE; - struct rpcrdma_regbuf *rb; - - if (req->rl_rdmabuf) - return true; - - rb = rpcrdma_alloc_regbuf(size, DMA_TO_DEVICE, flags); - if (IS_ERR(rb)) - return false; - - r_xprt->rx_stats.hardway_register_count += size; - req->rl_rdmabuf = rb; - xdr_buf_init(&req->rl_hdrbuf, rb->rg_base, rdmab_length(rb)); - return true; -} - static bool rpcrdma_get_sendbuf(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, size_t size, gfp_t flags) @@ -644,15 +618,11 @@ xprt_rdma_allocate(struct rpc_task *task) if (RPC_IS_SWAPPER(task)) flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN; - if (!rpcrdma_get_rdmabuf(r_xprt, req, flags)) - goto out_fail; if (!rpcrdma_get_sendbuf(r_xprt, req, rqst->rq_callsize, flags)) goto out_fail; if (!rpcrdma_get_recvbuf(r_xprt, req, rqst->rq_rcvsize, flags)) goto out_fail; - req->rl_cpu = smp_processor_id(); - req->rl_connect_cookie = 0; /* our reserved value */ rpcrdma_set_xprtdata(rqst, req); rqst->rq_buffer = req->rl_sendbuf->rg_base; rqst->rq_rbuffer = req->rl_recvbuf->rg_base; @@ -694,7 +664,8 @@ xprt_rdma_free(struct rpc_task *task) * Returns: * %0 if the RPC message has been sent * %-ENOTCONN if the caller should reconnect and call again - * %-ENOBUFS if the caller should call again later + * %-EAGAIN if the caller should call again + * %-ENOBUFS if the caller should call again after a delay * %-EIO if a permanent error occurred and the request was not * sent. Do not try to send this message again. */ @@ -723,9 +694,9 @@ xprt_rdma_send_request(struct rpc_task *task) rpcrdma_recv_buffer_get(req); /* Must suppress retransmit to maintain credits */ - if (req->rl_connect_cookie == xprt->connect_cookie) + if (rqst->rq_connect_cookie == xprt->connect_cookie) goto drop_connection; - req->rl_connect_cookie = xprt->connect_cookie; + rqst->rq_xtime = ktime_get(); __set_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags); if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req)) @@ -733,6 +704,12 @@ xprt_rdma_send_request(struct rpc_task *task) rqst->rq_xmit_bytes_sent += rqst->rq_snd_buf.len; rqst->rq_bytes_sent = 0; + + /* An RPC with no reply will throw off credit accounting, + * so drop the connection to reset the credit grant. + */ + if (!rpc_reply_expected(task)) + goto drop_connection; return 0; failed_marshal: diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index e6f84a6434a0..fe5eaca2d197 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -250,11 +250,11 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) wait_for_completion(&ia->ri_remove_done); ia->ri_id = NULL; - ia->ri_pd = NULL; ia->ri_device = NULL; /* Return 1 to ensure the core destroys the id. */ return 1; case RDMA_CM_EVENT_ESTABLISHED: + ++xprt->rx_xprt.connect_cookie; connstate = 1; rpcrdma_update_connect_private(xprt, &event->param.conn); goto connected; @@ -273,6 +273,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) connstate = -EAGAIN; goto connected; case RDMA_CM_EVENT_DISCONNECTED: + ++xprt->rx_xprt.connect_cookie; connstate = -ECONNABORTED; connected: xprt->rx_buf.rb_credits = 1; @@ -445,7 +446,9 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) ia->ri_id->qp = NULL; } ib_free_cq(ep->rep_attr.recv_cq); + ep->rep_attr.recv_cq = NULL; ib_free_cq(ep->rep_attr.send_cq); + ep->rep_attr.send_cq = NULL; /* The ULP is responsible for ensuring all DMA * mappings and MRs are gone. @@ -458,6 +461,8 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) rpcrdma_dma_unmap_regbuf(req->rl_recvbuf); } rpcrdma_mrs_destroy(buf); + ib_dealloc_pd(ia->ri_pd); + ia->ri_pd = NULL; /* Allow waiters to continue */ complete(&ia->ri_remove_done); @@ -589,11 +594,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* Client offers RDMA Read but does not initiate */ ep->rep_remote_cma.initiator_depth = 0; - if (ia->ri_device->attrs.max_qp_rd_atom > 32) /* arbitrary but <= 255 */ - ep->rep_remote_cma.responder_resources = 32; - else - ep->rep_remote_cma.responder_resources = - ia->ri_device->attrs.max_qp_rd_atom; + ep->rep_remote_cma.responder_resources = + min_t(int, U8_MAX, ia->ri_device->attrs.max_qp_rd_atom); /* Limit transport retries so client can detect server * GID changes quickly. RPC layer handles re-establishing @@ -628,14 +630,16 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { cancel_delayed_work_sync(&ep->rep_connect_worker); - if (ia->ri_id->qp) { + if (ia->ri_id && ia->ri_id->qp) { rpcrdma_ep_disconnect(ep, ia); rdma_destroy_qp(ia->ri_id); ia->ri_id->qp = NULL; } - ib_free_cq(ep->rep_attr.recv_cq); - ib_free_cq(ep->rep_attr.send_cq); + if (ep->rep_attr.recv_cq) + ib_free_cq(ep->rep_attr.recv_cq); + if (ep->rep_attr.send_cq) + ib_free_cq(ep->rep_attr.send_cq); } /* Re-establish a connection after a device removal event. @@ -1024,7 +1028,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) LIST_HEAD(free); LIST_HEAD(all); - for (count = 0; count < 32; count++) { + for (count = 0; count < 3; count++) { struct rpcrdma_mr *mr; int rc; @@ -1049,8 +1053,9 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) list_splice(&all, &buf->rb_all); r_xprt->rx_stats.mrs_allocated += count; spin_unlock(&buf->rb_mrlock); - trace_xprtrdma_createmrs(r_xprt, count); + + xprt_write_space(&r_xprt->rx_xprt); } static void @@ -1068,17 +1073,27 @@ struct rpcrdma_req * rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buffer = &r_xprt->rx_buf; + struct rpcrdma_regbuf *rb; struct rpcrdma_req *req; req = kzalloc(sizeof(*req), GFP_KERNEL); if (req == NULL) return ERR_PTR(-ENOMEM); + rb = rpcrdma_alloc_regbuf(RPCRDMA_HDRBUF_SIZE, + DMA_TO_DEVICE, GFP_KERNEL); + if (IS_ERR(rb)) { + kfree(req); + return ERR_PTR(-ENOMEM); + } + req->rl_rdmabuf = rb; + xdr_buf_init(&req->rl_hdrbuf, rb->rg_base, rdmab_length(rb)); + req->rl_buffer = buffer; + INIT_LIST_HEAD(&req->rl_registered); + spin_lock(&buffer->rb_reqslock); list_add(&req->rl_all, &buffer->rb_allreqs); spin_unlock(&buffer->rb_reqslock); - req->rl_buffer = &r_xprt->rx_buf; - INIT_LIST_HEAD(&req->rl_registered); return req; } @@ -1535,7 +1550,6 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct rpcrdma_req *req) { struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr; - struct ib_send_wr *send_wr_fail; int rc; if (req->rl_reply) { @@ -1554,7 +1568,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, --ep->rep_send_count; } - rc = ib_post_send(ia->ri_id->qp, send_wr, &send_wr_fail); + rc = ia->ri_ops->ro_send(ia, req); trace_xprtrdma_post_send(req, rc); if (rc) return -ENOTCONN; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 69883a960a3f..3d3b423fa9c1 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -334,8 +334,6 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { struct list_head rl_list; - int rl_cpu; - unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply; struct xdr_stream rl_stream; @@ -474,6 +472,8 @@ struct rpcrdma_memreg_ops { (*ro_map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool, struct rpcrdma_mr **); + int (*ro_send)(struct rpcrdma_ia *ia, + struct rpcrdma_req *req); void (*ro_reminv)(struct rpcrdma_rep *rep, struct list_head *mrs); void (*ro_unmap_sync)(struct rpcrdma_xprt *, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 956e29c1438d..c8902f11efdd 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -527,6 +527,7 @@ static int xs_local_send_request(struct rpc_task *task) xs_pktdump("packet data:", req->rq_svec->iov_base, req->rq_svec->iov_len); + req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, NULL, 0, xdr, req->rq_bytes_sent, true, &sent); dprintk("RPC: %s(%u) = %d\n", @@ -589,6 +590,7 @@ static int xs_udp_send_request(struct rpc_task *task) if (!xprt_bound(xprt)) return -ENOTCONN; + req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, xdr, req->rq_bytes_sent, true, &sent); @@ -678,6 +680,7 @@ static int xs_tcp_send_request(struct rpc_task *task) /* Continue transmitting the packet/record. We must be careful * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ + req->rq_xtime = ktime_get(); while (1) { sent = 0; status = xs_sendpages(transport->sock, NULL, 0, xdr, @@ -1060,6 +1063,7 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, if (!rovr) goto out_unlock; xprt_pin_rqst(rovr); + xprt_update_rtt(rovr->rq_task); spin_unlock(&xprt->recv_lock); task = rovr->rq_task; diff --git a/net/tipc/node.c b/net/tipc/node.c index 6f98b56dd48e..f29549de9245 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1950,6 +1950,7 @@ out: int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); + struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1]; struct tipc_nl_msg msg; char *name; int err; @@ -1957,9 +1958,19 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) msg.portid = info->snd_portid; msg.seq = info->snd_seq; - if (!info->attrs[TIPC_NLA_LINK_NAME]) + if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; - name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]); + + err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX, + info->attrs[TIPC_NLA_LINK], + tipc_nl_link_policy, info->extack); + if (err) + return err; + + if (!attrs[TIPC_NLA_LINK_NAME]) + return -EINVAL; + + name = nla_data(attrs[TIPC_NLA_LINK_NAME]); msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!msg.skb) @@ -2244,7 +2255,7 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); for (bearer_id = prev_bearer; bearer_id < MAX_BEARERS; bearer_id++) { - err = __tipc_nl_add_monitor(net, &msg, prev_bearer); + err = __tipc_nl_add_monitor(net, &msg, bearer_id); if (err) break; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 252a52ae0893..6be21575503a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1516,10 +1516,10 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) srcaddr->sock.family = AF_TIPC; srcaddr->sock.addrtype = TIPC_ADDR_ID; + srcaddr->sock.scope = 0; srcaddr->sock.addr.id.ref = msg_origport(hdr); srcaddr->sock.addr.id.node = msg_orignode(hdr); srcaddr->sock.addr.name.domain = 0; - srcaddr->sock.scope = 0; m->msg_namelen = sizeof(struct sockaddr_tipc); if (!msg_in_group(hdr)) @@ -1528,6 +1528,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) /* Group message users may also want to know sending member's id */ srcaddr->member.family = AF_TIPC; srcaddr->member.addrtype = TIPC_ADDR_NAME; + srcaddr->member.scope = 0; srcaddr->member.addr.name.name.type = msg_nametype(hdr); srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member; srcaddr->member.addr.name.domain = 0; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 0d379970960e..20cd93be6236 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -114,6 +114,7 @@ int tls_push_sg(struct sock *sk, size = sg->length - offset; offset += sg->offset; + ctx->in_tcp_sendpages = true; while (1) { if (sg_is_last(sg)) sendpage_flags = flags; @@ -134,6 +135,7 @@ retry: offset -= sg->offset; ctx->partially_sent_offset = offset; ctx->partially_sent_record = (void *)sg; + ctx->in_tcp_sendpages = false; return ret; } @@ -148,6 +150,8 @@ retry: } clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + ctx->in_tcp_sendpages = false; + ctx->sk_write_space(sk); return 0; } @@ -217,6 +221,10 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); + /* We are already sending pages, ignore notification */ + if (ctx->in_tcp_sendpages) + return; + if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; int rc; @@ -241,16 +249,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) struct tls_context *ctx = tls_get_ctx(sk); long timeo = sock_sndtimeo(sk, 0); void (*sk_proto_close)(struct sock *sk, long timeout); + bool free_ctx = false; lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if (ctx->conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - - if (ctx->conf == TLS_BASE) { - kfree(ctx); - ctx = NULL; + if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) { + free_ctx = true; goto skip_tx_cleanup; } @@ -287,7 +292,7 @@ skip_tx_cleanup: /* free ctx for TLS_HW_RECORD, used by tcp_set_state * for sk->sk_prot->unhash [tls_hw_unhash] */ - if (ctx && ctx->conf == TLS_HW_RECORD) + if (free_ctx) kfree(ctx); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f9d2f2233f09..6c177ae7a6d9 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2175,6 +2175,12 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) return afinfo; } +void xfrm_flush_gc(void) +{ + flush_work(&xfrm_state_gc_work); +} +EXPORT_SYMBOL(xfrm_flush_gc); + /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ void xfrm_state_delete_tunnel(struct xfrm_state *x) { |