diff options
Diffstat (limited to 'net')
70 files changed, 836 insertions, 455 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 98a30a5b8664..59555f0f8fc8 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -443,7 +443,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { - flgs = vlandev->flags; + flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4663c3dad3f5..c4802f3bd4c5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2854,9 +2854,11 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status, * state. If we were running both LE and BR/EDR inquiry * simultaneously, and BR/EDR inquiry is already * finished, stop discovery, otherwise BR/EDR inquiry - * will stop discovery when finished. + * will stop discovery when finished. If we will resolve + * remote device name, do not change discovery state. */ - if (!test_bit(HCI_INQUIRY, &hdev->flags)) + if (!test_bit(HCI_INQUIRY, &hdev->flags) && + hdev->discovery.state != DISCOVERY_RESOLVING) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } else { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e0670d7054f9..659fb96672e4 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -796,9 +796,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, int err = 0; if (ndm->ndm_flags & NTF_USE) { + local_bh_disable(); rcu_read_lock(); br_fdb_update(p->br, p, addr, vid, true); rcu_read_unlock(); + local_bh_enable(); } else { spin_lock_bh(&p->br->hash_lock); err = fdb_add_entry(p, addr, ndm->ndm_state, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 4b6722f8f179..ff667e18b2d6 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1072,7 +1072,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } @@ -1167,6 +1167,9 @@ static void br_multicast_add_router(struct net_bridge *br, struct net_bridge_port *p; struct hlist_node *slot = NULL; + if (!hlist_unhashed(&port->rlist)) + return; + hlist_for_each_entry(p, &br->router_list, rlist) { if ((unsigned long) port >= (unsigned long) p) break; @@ -1194,12 +1197,8 @@ static void br_multicast_mark_router(struct net_bridge *br, if (port->multicast_router != 1) return; - if (!hlist_unhashed(&port->rlist)) - goto timer; - br_multicast_add_router(br, port); -timer: mod_timer(&port->multicast_router_timer, now + br->multicast_querier_interval); } @@ -1822,7 +1821,7 @@ static void br_multicast_query_expired(struct net_bridge *br, if (query->startup_sent < br->multicast_startup_query_count) query->startup_sent++; - RCU_INIT_POINTER(querier, NULL); + RCU_INIT_POINTER(querier->port, NULL); br_multicast_send_query(br, NULL, query); spin_unlock(&br->multicast_lock); } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index ab55e2472beb..60ddfbeb47f5 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,10 +37,6 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> -#if IS_ENABLED(CONFIG_NF_CONNTRACK) -#include <net/netfilter/nf_conntrack.h> -#endif - #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL @@ -350,24 +346,15 @@ free_skb: return 0; } -static bool dnat_took_place(const struct sk_buff *skb) +static bool daddr_was_changed(const struct sk_buff *skb, + const struct nf_bridge_info *nf_bridge) { -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_untracked(ct)) - return false; - - return test_bit(IPS_DST_NAT_BIT, &ct->status); -#else - return false; -#endif + return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. + * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge @@ -421,7 +408,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) nf_bridge->pkt_otherhost = false; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - if (dnat_took_place(skb)) { + if (daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -632,6 +619,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { + struct nf_bridge_info *nf_bridge; struct net_bridge_port *p; struct net_bridge *br; __u32 len = nf_bridge_encap_header_len(skb); @@ -669,6 +657,9 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, if (!setup_pre_routing(skb)) return NF_DROP; + nf_bridge = nf_bridge_info_get(skb); + nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb, diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 4fcaa67750fd..7caf7fae2d5b 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -97,7 +97,9 @@ static void br_forward_delay_timer_expired(unsigned long arg) netif_carrier_on(br->dev); } br_log_state(p); + rcu_read_lock(); br_ifinfo_notify(RTM_NEWLINK, p); + rcu_read_unlock(); spin_unlock(&br->lock); } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 4ec0c803aef1..112ad784838a 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -373,6 +377,10 @@ static int caif_stream_recvmsg(struct socket *sock, struct msghdr *msg, struct sk_buff *skb; lock_sock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } skb = skb_dequeue(&sk->sk_receive_queue); caif_check_flow_release(sk); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 41a4abc7e98e..c4ec9239249a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1306,8 +1306,6 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, if (list_empty(&req->r_osd_item)) req->r_osd = NULL; } - - list_del_init(&req->r_req_lru_item); /* can be on notarget */ ceph_osdc_put_request(req); } @@ -2017,20 +2015,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, err = __map_request(osdc, req, force_resend || force_resend_writes); dout("__map_request returned %d\n", err); - if (err == 0) - continue; /* no change and no osd was specified */ if (err < 0) continue; /* hrm! */ - if (req->r_osd == NULL) { - dout("tid %llu maps to no valid osd\n", req->r_tid); - needmap++; /* request a newer map */ - continue; - } + if (req->r_osd == NULL || err > 0) { + if (req->r_osd == NULL) { + dout("lingering %p tid %llu maps to no osd\n", + req, req->r_tid); + /* + * A homeless lingering request makes + * no sense, as it's job is to keep + * a particular OSD connection open. + * Request a newer map and kick the + * request, knowing that it won't be + * resent until we actually get a map + * that can tell us where to send it. + */ + needmap++; + } - dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - __register_request(osdc, req); - __unregister_linger_request(osdc, req); + dout("kicking lingering %p tid %llu osd%d\n", req, + req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); + __register_request(osdc, req); + __unregister_linger_request(osdc, req); + } } reset_changed_osds(osdc); mutex_unlock(&osdc->request_mutex); diff --git a/net/core/dev.c b/net/core/dev.c index 2c1c67fad64d..aa82f9ab6a36 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1718,15 +1718,8 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, GFP_ATOMIC)) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } - } - - if (unlikely(!is_skb_forwardable(dev, skb))) { + if (skb_orphan_frags(skb, GFP_ATOMIC) || + unlikely(!is_skb_forwardable(dev, skb))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 508155b283dd..54817d365366 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2212,8 +2212,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) do { set_current_state(TASK_INTERRUPTIBLE); hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); - if (!hrtimer_active(&t.timer)) - t.task = NULL; if (likely(t.task)) schedule(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 666e0928ba40..8de36824018d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2416,6 +2416,9 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, { struct sk_buff *skb; + if (dev->reg_state != NETREG_REGISTERED) + return; + skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); if (skb) rtmsg_ifinfo_send(skb, dev, flags); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3cfff2a3d651..41ec02242ea7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4398,7 +4398,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, while (order) { if (npages >= 1 << order) { - page = alloc_pages(gfp_mask | + page = alloc_pages((gfp_mask & ~__GFP_WAIT) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, diff --git a/net/core/sock.c b/net/core/sock.c index 292f42228bfb..dc30dc5bb1b8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -354,15 +354,12 @@ void sk_clear_memalloc(struct sock *sk) /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward - * progress of swapping. However, if SOCK_MEMALLOC is cleared while - * it has rmem allocations there is a risk that the user of the - * socket cannot make forward progress due to exceeding the rmem - * limits. By rights, sk_clear_memalloc() should only be called - * on sockets being torn down but warn and reset the accounting if - * that assumption breaks. + * progress of swapping. SOCK_MEMALLOC may be cleared while + * it has rmem allocations due to the last swapfile being deactivated + * but there is a risk that the socket is unusable due to exceeding + * the rmem limits. Reclaim the reserves and obey rmem limits again. */ - if (WARN_ON(sk->sk_forward_alloc)) - sk_mem_reclaim(sk); + sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); @@ -1883,7 +1880,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER) { - pfrag->page = alloc_pages(gfp | __GFP_COMP | + pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index e6f6cc3a1bcf..392e29a0227d 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -359,7 +359,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, */ ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); if (ds == NULL) - return NULL; + return ERR_PTR(-ENOMEM); ds->dst = dst; ds->index = index; @@ -370,7 +370,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, ret = dsa_switch_setup_one(ds, parent); if (ret) - return NULL; + return ERR_PTR(ret); return ds; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 421a80b09b62..477937465a20 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -49,7 +49,7 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen) len = ALIGN(len, crypto_tfm_ctx_alignment()); } - len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead); + len += sizeof(struct aead_request) + crypto_aead_reqsize(aead); len = ALIGN(len, __alignof__(struct scatterlist)); len += sizeof(struct scatterlist) * nfrags; @@ -68,17 +68,6 @@ static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; } -static inline struct aead_givcrypt_request *esp_tmp_givreq( - struct crypto_aead *aead, u8 *iv) -{ - struct aead_givcrypt_request *req; - - req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead), - crypto_tfm_ctx_alignment()); - aead_givcrypt_set_tfm(req, aead); - return req; -} - static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) { struct aead_request *req; @@ -97,14 +86,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static inline struct scatterlist *esp_givreq_sg( - struct crypto_aead *aead, struct aead_givcrypt_request *req) -{ - return (void *)ALIGN((unsigned long)(req + 1) + - crypto_aead_reqsize(aead), - __alignof__(struct scatterlist)); -} - static void esp_output_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; @@ -113,14 +94,37 @@ static void esp_output_done(struct crypto_async_request *base, int err) xfrm_output_resume(skb, err); } +/* Move ESP header back into place. */ +static void esp_restore_header(struct sk_buff *skb, unsigned int offset) +{ + struct ip_esp_hdr *esph = (void *)(skb->data + offset); + void *tmp = ESP_SKB_CB(skb)->tmp; + __be32 *seqhi = esp_tmp_seqhi(tmp); + + esph->seq_no = esph->spi; + esph->spi = *seqhi; +} + +static void esp_output_restore_header(struct sk_buff *skb) +{ + esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32)); +} + +static void esp_output_done_esn(struct crypto_async_request *base, int err) +{ + struct sk_buff *skb = base->data; + + esp_output_restore_header(skb); + esp_output_done(base, err); +} + static int esp_output(struct xfrm_state *x, struct sk_buff *skb) { int err; struct ip_esp_hdr *esph; struct crypto_aead *aead; - struct aead_givcrypt_request *req; + struct aead_request *req; struct scatterlist *sg; - struct scatterlist *asg; struct sk_buff *trailer; void *tmp; u8 *iv; @@ -129,17 +133,19 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) int clen; int alen; int plen; + int ivlen; int tfclen; int nfrags; int assoclen; - int sglists; int seqhilen; __be32 *seqhi; + __be64 seqno; /* skb is pure payload to encrypt */ aead = x->data; alen = crypto_aead_authsize(aead); + ivlen = crypto_aead_ivsize(aead); tfclen = 0; if (x->tfcpad) { @@ -160,16 +166,14 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) nfrags = err; assoclen = sizeof(*esph); - sglists = 1; seqhilen = 0; if (x->props.flags & XFRM_STATE_ESN) { - sglists += 2; seqhilen += sizeof(__be32); assoclen += seqhilen; } - tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); + tmp = esp_alloc_tmp(aead, nfrags, seqhilen); if (!tmp) { err = -ENOMEM; goto error; @@ -177,9 +181,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); - req = esp_tmp_givreq(aead, iv); - asg = esp_givreq_sg(aead, req); - sg = asg + sglists; + req = esp_tmp_req(aead, iv); + sg = esp_req_sg(aead, req); /* Fill padding... */ tail = skb_tail_pointer(trailer); @@ -235,36 +238,53 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) *skb_mac_header(skb) = IPPROTO_UDP; } - esph->spi = x->id.spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); + aead_request_set_callback(req, 0, esp_output_done, skb); + + /* For ESN we move the header forward by 4 bytes to + * accomodate the high bits. We will move it back after + * encryption. + */ + if ((x->props.flags & XFRM_STATE_ESN)) { + esph = (void *)(skb_transport_header(skb) - sizeof(__be32)); + *seqhi = esph->spi; + esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + aead_request_set_callback(req, 0, esp_output_done_esn, skb); + } + + esph->spi = x->id.spi; + sg_init_table(sg, nfrags); skb_to_sgvec(skb, sg, - esph->enc_data + crypto_aead_ivsize(aead) - skb->data, - clen + alen); + (unsigned char *)esph - skb->data, + assoclen + ivlen + clen + alen); - if ((x->props.flags & XFRM_STATE_ESN)) { - sg_init_table(asg, 3); - sg_set_buf(asg, &esph->spi, sizeof(__be32)); - *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); - sg_set_buf(asg + 1, seqhi, seqhilen); - sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); - } else - sg_init_one(asg, esph, sizeof(*esph)); - - aead_givcrypt_set_callback(req, 0, esp_output_done, skb); - aead_givcrypt_set_crypt(req, sg, sg, clen, iv); - aead_givcrypt_set_assoc(req, asg, assoclen); - aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output.low); + aead_request_set_crypt(req, sg, sg, ivlen + clen, iv); + aead_request_set_ad(req, assoclen); + + seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low + + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); + + memset(iv, 0, ivlen); + memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8), + min(ivlen, 8)); ESP_SKB_CB(skb)->tmp = tmp; - err = crypto_aead_givencrypt(req); - if (err == -EINPROGRESS) + err = crypto_aead_encrypt(req); + + switch (err) { + case -EINPROGRESS: goto error; - if (err == -EBUSY) + case -EBUSY: err = NET_XMIT_DROP; + break; + + case 0: + if ((x->props.flags & XFRM_STATE_ESN)) + esp_output_restore_header(skb); + } kfree(tmp); @@ -363,6 +383,20 @@ static void esp_input_done(struct crypto_async_request *base, int err) xfrm_input_resume(skb, esp_input_done2(skb, err)); } +static void esp_input_restore_header(struct sk_buff *skb) +{ + esp_restore_header(skb, 0); + __skb_pull(skb, 4); +} + +static void esp_input_done_esn(struct crypto_async_request *base, int err) +{ + struct sk_buff *skb = base->data; + + esp_input_restore_header(skb); + esp_input_done(base, err); +} + /* * Note: detecting truncated vs. non-truncated authentication data is very * expensive, so we only support truncated data, which is the recommended @@ -374,19 +408,18 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) struct crypto_aead *aead = x->data; struct aead_request *req; struct sk_buff *trailer; - int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead); + int ivlen = crypto_aead_ivsize(aead); + int elen = skb->len - sizeof(*esph) - ivlen; int nfrags; int assoclen; - int sglists; int seqhilen; __be32 *seqhi; void *tmp; u8 *iv; struct scatterlist *sg; - struct scatterlist *asg; int err = -EINVAL; - if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) + if (!pskb_may_pull(skb, sizeof(*esph) + ivlen)) goto out; if (elen <= 0) @@ -399,17 +432,15 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) nfrags = err; assoclen = sizeof(*esph); - sglists = 1; seqhilen = 0; if (x->props.flags & XFRM_STATE_ESN) { - sglists += 2; seqhilen += sizeof(__be32); assoclen += seqhilen; } err = -ENOMEM; - tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); + tmp = esp_alloc_tmp(aead, nfrags, seqhilen); if (!tmp) goto out; @@ -417,36 +448,39 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); - asg = esp_req_sg(aead, req); - sg = asg + sglists; + sg = esp_req_sg(aead, req); skb->ip_summed = CHECKSUM_NONE; esph = (struct ip_esp_hdr *)skb->data; - /* Get ivec. This can be wrong, check against another impls. */ - iv = esph->enc_data; - - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen); + aead_request_set_callback(req, 0, esp_input_done, skb); + /* For ESN we move the header forward by 4 bytes to + * accomodate the high bits. We will move it back after + * decryption. + */ if ((x->props.flags & XFRM_STATE_ESN)) { - sg_init_table(asg, 3); - sg_set_buf(asg, &esph->spi, sizeof(__be32)); - *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; - sg_set_buf(asg + 1, seqhi, seqhilen); - sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); - } else - sg_init_one(asg, esph, sizeof(*esph)); + esph = (void *)skb_push(skb, 4); + *seqhi = esph->spi; + esph->spi = esph->seq_no; + esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + aead_request_set_callback(req, 0, esp_input_done_esn, skb); + } - aead_request_set_callback(req, 0, esp_input_done, skb); - aead_request_set_crypt(req, sg, sg, elen, iv); - aead_request_set_assoc(req, asg, assoclen); + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); + + aead_request_set_crypt(req, sg, sg, elen + ivlen, iv); + aead_request_set_ad(req, assoclen); err = crypto_aead_decrypt(req); if (err == -EINPROGRESS) goto out; + if ((x->props.flags & XFRM_STATE_ESN)) + esp_input_restore_header(skb); + err = esp_input_done2(skb, err); out: @@ -518,10 +552,16 @@ static void esp_destroy(struct xfrm_state *x) static int esp_init_aead(struct xfrm_state *x) { + char aead_name[CRYPTO_MAX_ALG_NAME]; struct crypto_aead *aead; int err; - aead = crypto_alloc_aead(x->aead->alg_name, 0, 0); + err = -ENAMETOOLONG; + if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", + x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME) + goto error; + + aead = crypto_alloc_aead(aead_name, 0, 0); err = PTR_ERR(aead); if (IS_ERR(aead)) goto error; @@ -560,15 +600,19 @@ static int esp_init_authenc(struct xfrm_state *x) if ((x->props.flags & XFRM_STATE_ESN)) { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, - "authencesn(%s,%s)", + "%s%sauthencesn(%s,%s)%s", + x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", - x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + x->ealg->alg_name, + x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) goto error; } else { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, - "authenc(%s,%s)", + "%s%sauthenc(%s,%s)%s", + x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", - x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + x->ealg->alg_name, + x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) goto error; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e13fcc602da2..09b62e17dd8c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1164,6 +1164,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; + new_fa->tb_id = tb->tb_id; err = netdev_switch_fib_ipv4_add(key, plen, fi, new_fa->fa_tos, @@ -1764,7 +1765,7 @@ void fib_table_flush_external(struct fib_table *tb) /* record local slen */ slen = fa->fa_slen; - if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL)) + if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD)) continue; netdev_switch_fib_ipv4_del(n->key, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9f7269f3c54a..0c152087ca15 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -65,7 +65,6 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, goto drop; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; - skb->mark = be32_to_cpu(tunnel->parms.i_key); return xfrm_input(skb, nexthdr, spi, encap_type); } @@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) struct pcpu_sw_netstats *tstats; struct xfrm_state *x; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + u32 orig_mark = skb->mark; + int ret; if (!tunnel) return 1; @@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) x = xfrm_input_state(skb); family = x->inner_mode->afinfo->family; - if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + skb->mark = be32_to_cpu(tunnel->parms.i_key); + ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); + skb->mark = orig_mark; + + if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); @@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl, 0, sizeof(fl)); - skb->mark = be32_to_cpu(tunnel->parms.o_key); - switch (skb->protocol) { case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); @@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + /* override mark with tunnel output key */ + fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); + return vti_xmit(skb, dev, &fl); } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 13bfe84bf3ca..a61200754f4b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1075,6 +1075,9 @@ static int do_replace(struct net *net, const void __user *user, /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1499,6 +1502,9 @@ static int compat_do_replace(struct net *net, void __user *user, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index c69db7fa25ee..2d0e265fef6e 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1262,6 +1262,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1809,6 +1812,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bff62fc87b8e..f45f2a12f37b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -902,6 +902,10 @@ static int ip_error(struct sk_buff *skb) bool send; int code; + /* IP on this device is disabled. */ + if (!in_dev) + goto out; + net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46efa03d2b11..f1377f2a0472 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -402,6 +402,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; + u64_stats_init(&tp->syncp); tp->reordering = sysctl_tcp_reordering; tcp_enable_early_retrans(tp); @@ -2598,6 +2599,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; + unsigned int start; u32 rate; memset(info, 0, sizeof(*info)); @@ -2665,10 +2667,11 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) rate = READ_ONCE(sk->sk_max_pacing_rate); info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; - spin_lock_bh(&sk->sk_lock.slock); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; - spin_unlock_bh(&sk->sk_lock.slock); + do { + start = u64_stats_fetch_begin_irq(&tp->syncp); + info->tcpi_bytes_acked = tp->bytes_acked; + info->tcpi_bytes_received = tp->bytes_received; + } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 7a5ae50c80c8..84be008c945c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -187,6 +187,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; + icsk->icsk_ca_setsockopt = 1; if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); @@ -335,8 +336,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) rcu_read_lock(); ca = __tcp_ca_find_autoload(name); /* No change asking for existing value */ - if (ca == icsk->icsk_ca_ops) + if (ca == icsk->icsk_ca_ops) { + icsk->icsk_ca_setsockopt = 1; goto out; + } if (!ca) err = -ENOENT; else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3c673d5e6cff..46b087a27503 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -206,6 +206,10 @@ static bool tcp_fastopen_create_child(struct sock *sk, skb_set_owner_r(skb2, child); __skb_queue_tail(&child->sk_receive_queue, skb2); tp->syn_data_acked = 1; + + /* u64_stats_update_begin(&tp->syncp) not needed here, + * as we certainly are not changing upper 32bit value (0) + */ tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1; } else { end_seq = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bc790ea9960f..c9ab964189a0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2698,16 +2698,21 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); + if ((flag & FLAG_SND_UNA_ADVANCED) && + tcp_try_undo_loss(sk, false)) + return; + if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ /* Step 3.b. A timeout is spurious if not all data are * lost, i.e., never-retransmitted data are (s)acked. */ - if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) return; - if (after(tp->snd_nxt, tp->high_seq) && - (flag & FLAG_DATA_SACKED || is_dupack)) { - tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ + if (after(tp->snd_nxt, tp->high_seq)) { + if (flag & FLAG_DATA_SACKED || is_dupack) + tp->frto = 0; /* Step 3.a. loss was real */ } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) { tp->high_seq = tp->snd_nxt; __tcp_push_pending_frames(sk, tcp_current_mss(sk), @@ -2732,8 +2737,6 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) else if (flag & FLAG_SND_UNA_ADVANCED) tcp_reset_reno_sack(tp); } - if (tcp_try_undo_loss(sk, false)) - return; tcp_xmit_retransmit_queue(sk); } @@ -3283,7 +3286,9 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) { u32 delta = ack - tp->snd_una; + u64_stats_update_begin(&tp->syncp); tp->bytes_acked += delta; + u64_stats_update_end(&tp->syncp); tp->snd_una = ack; } @@ -3292,7 +3297,9 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { u32 delta = seq - tp->rcv_nxt; + u64_stats_update_begin(&tp->syncp); tp->bytes_received += delta; + u64_stats_update_end(&tp->syncp); tp->rcv_nxt = seq; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e5d7649136fc..17e7339ee5ca 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -300,7 +300,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_daddr = sk->sk_v6_daddr; tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; - tw->tw_flowlabel = np->flow_label >> 12; + tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK); tw->tw_ipv6only = sk->sk_ipv6only; } #endif @@ -420,7 +420,10 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) rcu_read_unlock(); } - if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner)) + /* If no valid choice made yet, assign current system default ca. */ + if (!ca_got_dst && + (!icsk->icsk_ca_setsockopt || + !try_module_get(icsk->icsk_ca_ops->owner))) tcp_assign_congestion_control(sk); tcp_set_ca_state(sk, TCP_CA_Open); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d10b7e0112eb..83aa604f9273 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -90,6 +90,7 @@ #include <linux/socket.h> #include <linux/sockios.h> #include <linux/igmp.h> +#include <linux/inetdevice.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/timer.h> @@ -1345,10 +1346,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -1962,6 +1961,7 @@ void udp_v4_early_demux(struct sk_buff *skb) struct sock *sk; struct dst_entry *dst; int dif = skb->dev->ifindex; + int ours; /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) @@ -1971,14 +1971,24 @@ void udp_v4_early_demux(struct sk_buff *skb) uh = udp_hdr(skb); if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) + skb->pkt_type == PACKET_MULTICAST) { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + + if (!in_dev) + return; + + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); - else if (skb->pkt_type == PACKET_HOST) + } else if (skb->pkt_type == PACKET_HOST) { sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); - else + } else { return; + } if (!sk) return; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index d873ceea86e6..ca09bf49ac68 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -133,6 +133,14 @@ static void snmp6_free_dev(struct inet6_dev *idev) free_percpu(idev->stats.ipv6); } +static void in6_dev_finish_destroy_rcu(struct rcu_head *head) +{ + struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); + + snmp6_free_dev(idev); + kfree(idev); +} + /* Nobody refers to this device, we may destroy it. */ void in6_dev_finish_destroy(struct inet6_dev *idev) @@ -151,7 +159,6 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) pr_warn("Freeing alive inet6 device %p\n", idev); return; } - snmp6_free_dev(idev); - kfree_rcu(idev, rcu); + call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } EXPORT_SYMBOL(in6_dev_finish_destroy); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 31f1b5d5e2ef..060a60b2f8a6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -76,7 +76,7 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqihlen) len = ALIGN(len, crypto_tfm_ctx_alignment()); } - len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead); + len += sizeof(struct aead_request) + crypto_aead_reqsize(aead); len = ALIGN(len, __alignof__(struct scatterlist)); len += sizeof(struct scatterlist) * nfrags; @@ -96,17 +96,6 @@ static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; } -static inline struct aead_givcrypt_request *esp_tmp_givreq( - struct crypto_aead *aead, u8 *iv) -{ - struct aead_givcrypt_request *req; - - req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead), - crypto_tfm_ctx_alignment()); - aead_givcrypt_set_tfm(req, aead); - return req; -} - static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) { struct aead_request *req; @@ -125,14 +114,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static inline struct scatterlist *esp_givreq_sg( - struct crypto_aead *aead, struct aead_givcrypt_request *req) -{ - return (void *)ALIGN((unsigned long)(req + 1) + - crypto_aead_reqsize(aead), - __alignof__(struct scatterlist)); -} - static void esp_output_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; @@ -141,32 +122,57 @@ static void esp_output_done(struct crypto_async_request *base, int err) xfrm_output_resume(skb, err); } +/* Move ESP header back into place. */ +static void esp_restore_header(struct sk_buff *skb, unsigned int offset) +{ + struct ip_esp_hdr *esph = (void *)(skb->data + offset); + void *tmp = ESP_SKB_CB(skb)->tmp; + __be32 *seqhi = esp_tmp_seqhi(tmp); + + esph->seq_no = esph->spi; + esph->spi = *seqhi; +} + +static void esp_output_restore_header(struct sk_buff *skb) +{ + esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32)); +} + +static void esp_output_done_esn(struct crypto_async_request *base, int err) +{ + struct sk_buff *skb = base->data; + + esp_output_restore_header(skb); + esp_output_done(base, err); +} + static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) { int err; struct ip_esp_hdr *esph; struct crypto_aead *aead; - struct aead_givcrypt_request *req; + struct aead_request *req; struct scatterlist *sg; - struct scatterlist *asg; struct sk_buff *trailer; void *tmp; int blksize; int clen; int alen; int plen; + int ivlen; int tfclen; int nfrags; int assoclen; - int sglists; int seqhilen; u8 *iv; u8 *tail; __be32 *seqhi; + __be64 seqno; /* skb is pure payload to encrypt */ aead = x->data; alen = crypto_aead_authsize(aead); + ivlen = crypto_aead_ivsize(aead); tfclen = 0; if (x->tfcpad) { @@ -187,16 +193,14 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) nfrags = err; assoclen = sizeof(*esph); - sglists = 1; seqhilen = 0; if (x->props.flags & XFRM_STATE_ESN) { - sglists += 2; seqhilen += sizeof(__be32); assoclen += seqhilen; } - tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); + tmp = esp_alloc_tmp(aead, nfrags, seqhilen); if (!tmp) { err = -ENOMEM; goto error; @@ -204,9 +208,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); - req = esp_tmp_givreq(aead, iv); - asg = esp_givreq_sg(aead, req); - sg = asg + sglists; + req = esp_tmp_req(aead, iv); + sg = esp_req_sg(aead, req); /* Fill padding... */ tail = skb_tail_pointer(trailer); @@ -227,36 +230,53 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) esph = ip_esp_hdr(skb); *skb_mac_header(skb) = IPPROTO_ESP; - esph->spi = x->id.spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); + aead_request_set_callback(req, 0, esp_output_done, skb); + + /* For ESN we move the header forward by 4 bytes to + * accomodate the high bits. We will move it back after + * encryption. + */ + if ((x->props.flags & XFRM_STATE_ESN)) { + esph = (void *)(skb_transport_header(skb) - sizeof(__be32)); + *seqhi = esph->spi; + esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + aead_request_set_callback(req, 0, esp_output_done_esn, skb); + } + + esph->spi = x->id.spi; + sg_init_table(sg, nfrags); skb_to_sgvec(skb, sg, - esph->enc_data + crypto_aead_ivsize(aead) - skb->data, - clen + alen); + (unsigned char *)esph - skb->data, + assoclen + ivlen + clen + alen); - if ((x->props.flags & XFRM_STATE_ESN)) { - sg_init_table(asg, 3); - sg_set_buf(asg, &esph->spi, sizeof(__be32)); - *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); - sg_set_buf(asg + 1, seqhi, seqhilen); - sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); - } else - sg_init_one(asg, esph, sizeof(*esph)); - - aead_givcrypt_set_callback(req, 0, esp_output_done, skb); - aead_givcrypt_set_crypt(req, sg, sg, clen, iv); - aead_givcrypt_set_assoc(req, asg, assoclen); - aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output.low); + aead_request_set_crypt(req, sg, sg, ivlen + clen, iv); + aead_request_set_ad(req, assoclen); + + seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low + + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); + + memset(iv, 0, ivlen); + memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8), + min(ivlen, 8)); ESP_SKB_CB(skb)->tmp = tmp; - err = crypto_aead_givencrypt(req); - if (err == -EINPROGRESS) + err = crypto_aead_encrypt(req); + + switch (err) { + case -EINPROGRESS: goto error; - if (err == -EBUSY) + case -EBUSY: err = NET_XMIT_DROP; + break; + + case 0: + if ((x->props.flags & XFRM_STATE_ESN)) + esp_output_restore_header(skb); + } kfree(tmp); @@ -317,25 +337,38 @@ static void esp_input_done(struct crypto_async_request *base, int err) xfrm_input_resume(skb, esp_input_done2(skb, err)); } +static void esp_input_restore_header(struct sk_buff *skb) +{ + esp_restore_header(skb, 0); + __skb_pull(skb, 4); +} + +static void esp_input_done_esn(struct crypto_async_request *base, int err) +{ + struct sk_buff *skb = base->data; + + esp_input_restore_header(skb); + esp_input_done(base, err); +} + static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) { struct ip_esp_hdr *esph; struct crypto_aead *aead = x->data; struct aead_request *req; struct sk_buff *trailer; - int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead); + int ivlen = crypto_aead_ivsize(aead); + int elen = skb->len - sizeof(*esph) - ivlen; int nfrags; int assoclen; - int sglists; int seqhilen; int ret = 0; void *tmp; __be32 *seqhi; u8 *iv; struct scatterlist *sg; - struct scatterlist *asg; - if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) { + if (!pskb_may_pull(skb, sizeof(*esph) + ivlen)) { ret = -EINVAL; goto out; } @@ -354,16 +387,14 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) ret = -ENOMEM; assoclen = sizeof(*esph); - sglists = 1; seqhilen = 0; if (x->props.flags & XFRM_STATE_ESN) { - sglists += 2; seqhilen += sizeof(__be32); assoclen += seqhilen; } - tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); + tmp = esp_alloc_tmp(aead, nfrags, seqhilen); if (!tmp) goto out; @@ -371,36 +402,39 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); - asg = esp_req_sg(aead, req); - sg = asg + sglists; + sg = esp_req_sg(aead, req); skb->ip_summed = CHECKSUM_NONE; esph = (struct ip_esp_hdr *)skb->data; - /* Get ivec. This can be wrong, check against another impls. */ - iv = esph->enc_data; - - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen); + aead_request_set_callback(req, 0, esp_input_done, skb); + /* For ESN we move the header forward by 4 bytes to + * accomodate the high bits. We will move it back after + * decryption. + */ if ((x->props.flags & XFRM_STATE_ESN)) { - sg_init_table(asg, 3); - sg_set_buf(asg, &esph->spi, sizeof(__be32)); - *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; - sg_set_buf(asg + 1, seqhi, seqhilen); - sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); - } else - sg_init_one(asg, esph, sizeof(*esph)); + esph = (void *)skb_push(skb, 4); + *seqhi = esph->spi; + esph->spi = esph->seq_no; + esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + aead_request_set_callback(req, 0, esp_input_done_esn, skb); + } - aead_request_set_callback(req, 0, esp_input_done, skb); - aead_request_set_crypt(req, sg, sg, elen, iv); - aead_request_set_assoc(req, asg, assoclen); + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); + + aead_request_set_crypt(req, sg, sg, elen + ivlen, iv); + aead_request_set_ad(req, assoclen); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) goto out; + if ((x->props.flags & XFRM_STATE_ESN)) + esp_input_restore_header(skb); + ret = esp_input_done2(skb, ret); out: @@ -460,10 +494,16 @@ static void esp6_destroy(struct xfrm_state *x) static int esp_init_aead(struct xfrm_state *x) { + char aead_name[CRYPTO_MAX_ALG_NAME]; struct crypto_aead *aead; int err; - aead = crypto_alloc_aead(x->aead->alg_name, 0, 0); + err = -ENAMETOOLONG; + if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", + x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME) + goto error; + + aead = crypto_alloc_aead(aead_name, 0, 0); err = PTR_ERR(aead); if (IS_ERR(aead)) goto error; @@ -502,15 +542,19 @@ static int esp_init_authenc(struct xfrm_state *x) if ((x->props.flags & XFRM_STATE_ESN)) { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, - "authencesn(%s,%s)", + "%s%sauthencesn(%s,%s)%s", + x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", - x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + x->ealg->alg_name, + x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) goto error; } else { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, - "authenc(%s,%s)", + "%s%sauthenc(%s,%s)%s", + x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", - x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + x->ealg->alg_name, + x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) goto error; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 96dbffff5a24..bde57b113009 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -693,6 +693,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, { struct rt6_info *iter = NULL; struct rt6_info **ins; + struct rt6_info **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -716,8 +717,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (iter->dst.dev == rt->dst.dev && @@ -753,9 +759,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (iter->rt6i_metric > rt->rt6i_metric) break; +next_iter: ins = &iter->dst.rt6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = *ins; + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; @@ -815,6 +829,8 @@ add: } } else { + int nsiblings; + if (!found) { if (add) goto add; @@ -835,8 +851,27 @@ add: info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->rt6i_nsiblings; fib6_purge_rt(iter, fn, info->nl_net); rt6_release(iter); + + if (nsiblings) { + /* Replacing an ECMP route, remove all siblings */ + ins = &rt->dst.rt6_next; + iter = *ins; + while (iter) { + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->dst.rt6_next; + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); + nsiblings--; + } else { + ins = &iter->dst.rt6_next; + } + iter = *ins; + } + WARN_ON(nsiblings != 0); + } } return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c21777565c58..bc09cb97b840 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1300,8 +1300,10 @@ emsgsize: /* If this is the first and only packet and device * supports checksum offloading, let's use it. + * Use transhdrlen, same as IPv4, because partial + * sums only work when transhdrlen is set. */ - if (!skb && sk->sk_protocol == IPPROTO_UDP && + if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && length + fragheaderlen < mtu && rt->dst.dev->features & NETIF_F_V6_CSUM && !exthdrlen) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index ed9d681207fa..0224c032dca5 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -322,7 +322,6 @@ static int vti6_rcv(struct sk_buff *skb) } XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; - skb->mark = be32_to_cpu(t->parms.i_key); rcu_read_unlock(); @@ -342,6 +341,8 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) struct pcpu_sw_netstats *tstats; struct xfrm_state *x; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; + u32 orig_mark = skb->mark; + int ret; if (!t) return 1; @@ -358,7 +359,11 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) x = xfrm_input_state(skb); family = x->inner_mode->afinfo->family; - if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + skb->mark = be32_to_cpu(t->parms.i_key); + ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); + skb->mark = orig_mark; + + if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); @@ -430,6 +435,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct net_device *tdev; struct xfrm_state *x; int err = -1; + int mtu; if (!dst) goto tx_err_link_failure; @@ -463,6 +469,19 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; + mtu = dst_mtu(dst); + if (!skb->ignore_df && skb->len > mtu) { + skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu); + + if (skb->protocol == htons(ETH_P_IPV6)) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + else + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + + return -EMSGSIZE; + } + err = dst_output(skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); @@ -495,7 +514,6 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) int ret; memset(&fl, 0, sizeof(fl)); - skb->mark = be32_to_cpu(t->parms.o_key); switch (skb->protocol) { case htons(ETH_P_IPV6): @@ -516,6 +534,9 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err; } + /* override mark with tunnel output key */ + fl.flowi_mark = be32_to_cpu(t->parms.o_key); + ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 1a732a1d3c8e..62f5b0d0bc9b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1275,6 +1275,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1822,6 +1825,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d3588885f097..c73ae5039e46 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2504,9 +2504,9 @@ static int ip6_route_multipath(struct fib6_config *cfg, int add) int attrlen; int err = 0, last_err = 0; + remaining = cfg->fc_mp_len; beginning: rtnh = (struct rtnexthop *)cfg->fc_mp; - remaining = cfg->fc_mp_len; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { @@ -2536,15 +2536,19 @@ beginning: * next hops that have been already added. */ add = 0; + remaining = cfg->fc_mp_len - remaining; goto beginning; } } /* Because each route is added like a single route we remove - * this flag after the first nexthop (if there is a collision, - * we have already fail to add the first nexthop: - * fib6_add_rt2node() has reject it). + * these flags after the first nexthop: if there is a collision, + * we have already failed to add the first nexthop: + * fib6_add_rt2node() has rejected it; when replacing, old + * nexthops have been replaced by first new, the rest should + * be added to it. */ - cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | + NLM_F_REPLACE); rtnh = rtnh_next(rtnh, &remaining); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6575d665568..3adffb300238 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -914,7 +914,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, (tw->tw_flowlabel << 12)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3477c919fcc8..e51fc3eee6db 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -525,10 +525,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -731,7 +729,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || - (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) || + (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; if (!inet6_mc_check(sk, loc_addr, rmt_addr)) return false; diff --git a/net/key/af_key.c b/net/key/af_key.c index f0d52d721b3a..3c5b8ce38ef4 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1190,6 +1190,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, memcpy(x->ealg->alg_key, key+1, keysize); } x->props.ealgo = sa->sadb_sa_encrypt; + x->geniv = a->uinfo.encr.geniv; } } /* x->algo.flags = sa->sadb_sa_flags; */ diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index 208df7c0b6ea..7663c28ba353 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -11,9 +11,8 @@ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/crypto.h> #include <linux/err.h> -#include <crypto/aes.h> +#include <crypto/aead.h> #include <net/mac80211.h> #include "key.h" @@ -23,7 +22,7 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, u8 *data, size_t data_len, u8 *mic, size_t mic_len) { - struct scatterlist assoc, pt, ct[2]; + struct scatterlist sg[3]; char aead_req_data[sizeof(struct aead_request) + crypto_aead_reqsize(tfm)] @@ -32,15 +31,14 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, memset(aead_req, 0, sizeof(aead_req_data)); - sg_init_one(&pt, data, data_len); - sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); - sg_init_table(ct, 2); - sg_set_buf(&ct[0], data, data_len); - sg_set_buf(&ct[1], mic, mic_len); + sg_init_table(sg, 3); + sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad)); + sg_set_buf(&sg[1], data, data_len); + sg_set_buf(&sg[2], mic, mic_len); aead_request_set_tfm(aead_req, tfm); - aead_request_set_assoc(aead_req, &assoc, assoc.length); - aead_request_set_crypt(aead_req, &pt, ct, data_len, b_0); + aead_request_set_crypt(aead_req, sg, sg, data_len, b_0); + aead_request_set_ad(aead_req, sg[0].length); crypto_aead_encrypt(aead_req); } @@ -49,7 +47,7 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, u8 *data, size_t data_len, u8 *mic, size_t mic_len) { - struct scatterlist assoc, pt, ct[2]; + struct scatterlist sg[3]; char aead_req_data[sizeof(struct aead_request) + crypto_aead_reqsize(tfm)] __aligned(__alignof__(struct aead_request)); @@ -60,15 +58,14 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, memset(aead_req, 0, sizeof(aead_req_data)); - sg_init_one(&pt, data, data_len); - sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); - sg_init_table(ct, 2); - sg_set_buf(&ct[0], data, data_len); - sg_set_buf(&ct[1], mic, mic_len); + sg_init_table(sg, 3); + sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad)); + sg_set_buf(&sg[1], data, data_len); + sg_set_buf(&sg[2], mic, mic_len); aead_request_set_tfm(aead_req, tfm); - aead_request_set_assoc(aead_req, &assoc, assoc.length); - aead_request_set_crypt(aead_req, ct, &pt, data_len + mic_len, b_0); + aead_request_set_crypt(aead_req, sg, sg, data_len + mic_len, b_0); + aead_request_set_ad(aead_req, sg[0].length); return crypto_aead_decrypt(aead_req); } diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c index fd278bbe1b0d..3afe361fd27c 100644 --- a/net/mac80211/aes_gcm.c +++ b/net/mac80211/aes_gcm.c @@ -8,9 +8,8 @@ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/crypto.h> #include <linux/err.h> -#include <crypto/aes.h> +#include <crypto/aead.h> #include <net/mac80211.h> #include "key.h" @@ -19,7 +18,7 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, u8 *data, size_t data_len, u8 *mic) { - struct scatterlist assoc, pt, ct[2]; + struct scatterlist sg[3]; char aead_req_data[sizeof(struct aead_request) + crypto_aead_reqsize(tfm)] @@ -28,15 +27,14 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, memset(aead_req, 0, sizeof(aead_req_data)); - sg_init_one(&pt, data, data_len); - sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); - sg_init_table(ct, 2); - sg_set_buf(&ct[0], data, data_len); - sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN); + sg_init_table(sg, 3); + sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad)); + sg_set_buf(&sg[1], data, data_len); + sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); aead_request_set_tfm(aead_req, tfm); - aead_request_set_assoc(aead_req, &assoc, assoc.length); - aead_request_set_crypt(aead_req, &pt, ct, data_len, j_0); + aead_request_set_crypt(aead_req, sg, sg, data_len, j_0); + aead_request_set_ad(aead_req, sg[0].length); crypto_aead_encrypt(aead_req); } @@ -44,7 +42,7 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, u8 *data, size_t data_len, u8 *mic) { - struct scatterlist assoc, pt, ct[2]; + struct scatterlist sg[3]; char aead_req_data[sizeof(struct aead_request) + crypto_aead_reqsize(tfm)] __aligned(__alignof__(struct aead_request)); @@ -55,16 +53,15 @@ int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, memset(aead_req, 0, sizeof(aead_req_data)); - sg_init_one(&pt, data, data_len); - sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); - sg_init_table(ct, 2); - sg_set_buf(&ct[0], data, data_len); - sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN); + sg_init_table(sg, 3); + sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad)); + sg_set_buf(&sg[1], data, data_len); + sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); aead_request_set_tfm(aead_req, tfm); - aead_request_set_assoc(aead_req, &assoc, assoc.length); - aead_request_set_crypt(aead_req, ct, &pt, + aead_request_set_crypt(aead_req, sg, sg, data_len + IEEE80211_GCMP_MIC_LEN, j_0); + aead_request_set_ad(aead_req, sg[0].length); return crypto_aead_decrypt(aead_req); } diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c index f1321b7d6506..3ddd927aaf30 100644 --- a/net/mac80211/aes_gmac.c +++ b/net/mac80211/aes_gmac.c @@ -9,8 +9,8 @@ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/crypto.h> #include <linux/err.h> +#include <crypto/aead.h> #include <crypto/aes.h> #include <net/mac80211.h> @@ -24,7 +24,7 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, const u8 *data, size_t data_len, u8 *mic) { - struct scatterlist sg[3], ct[1]; + struct scatterlist sg[4]; char aead_req_data[sizeof(struct aead_request) + crypto_aead_reqsize(tfm)] __aligned(__alignof__(struct aead_request)); @@ -37,21 +37,19 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, memset(aead_req, 0, sizeof(aead_req_data)); memset(zero, 0, GMAC_MIC_LEN); - sg_init_table(sg, 3); + sg_init_table(sg, 4); sg_set_buf(&sg[0], aad, AAD_LEN); sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); memcpy(iv, nonce, GMAC_NONCE_LEN); memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN); iv[AES_BLOCK_SIZE - 1] = 0x01; - sg_init_table(ct, 1); - sg_set_buf(&ct[0], mic, GMAC_MIC_LEN); - aead_request_set_tfm(aead_req, tfm); - aead_request_set_assoc(aead_req, sg, AAD_LEN + data_len); - aead_request_set_crypt(aead_req, NULL, ct, 0, iv); + aead_request_set_crypt(aead_req, sg, sg, 0, iv); + aead_request_set_ad(aead_req, AAD_LEN + data_len); crypto_aead_encrypt(aead_req); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 265e42721a66..ff347a0eebd4 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2495,51 +2495,22 @@ static bool ieee80211_coalesce_started_roc(struct ieee80211_local *local, struct ieee80211_roc_work *new_roc, struct ieee80211_roc_work *cur_roc) { - unsigned long j = jiffies; - unsigned long cur_roc_end = cur_roc->hw_start_time + - msecs_to_jiffies(cur_roc->duration); - struct ieee80211_roc_work *next_roc; - int new_dur; + unsigned long now = jiffies; + unsigned long remaining = cur_roc->hw_start_time + + msecs_to_jiffies(cur_roc->duration) - + now; if (WARN_ON(!cur_roc->started || !cur_roc->hw_begun)) return false; - if (time_after(j + IEEE80211_ROC_MIN_LEFT, cur_roc_end)) + /* if it doesn't fit entirely, schedule a new one */ + if (new_roc->duration > jiffies_to_msecs(remaining)) return false; ieee80211_handle_roc_started(new_roc); - new_dur = new_roc->duration - jiffies_to_msecs(cur_roc_end - j); - - /* cur_roc is long enough - add new_roc to the dependents list. */ - if (new_dur <= 0) { - list_add_tail(&new_roc->list, &cur_roc->dependents); - return true; - } - - new_roc->duration = new_dur; - - /* - * if cur_roc was already coalesced before, we might - * want to extend the next roc instead of adding - * a new one. - */ - next_roc = list_entry(cur_roc->list.next, - struct ieee80211_roc_work, list); - if (&next_roc->list != &local->roc_list && - next_roc->chan == new_roc->chan && - next_roc->sdata == new_roc->sdata && - !WARN_ON(next_roc->started)) { - list_add_tail(&new_roc->list, &next_roc->dependents); - next_roc->duration = max(next_roc->duration, - new_roc->duration); - next_roc->type = max(next_roc->type, new_roc->type); - return true; - } - - /* add right after cur_roc */ - list_add(&new_roc->list, &cur_roc->list); - + /* add to dependents so we send the expired event properly */ + list_add_tail(&new_roc->list, &cur_roc->dependents); return true; } @@ -2652,17 +2623,9 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, * In the offloaded ROC case, if it hasn't begun, add * this new one to the dependent list to be handled * when the master one begins. If it has begun, - * check that there's still a minimum time left and - * if so, start this one, transmitting the frame, but - * add it to the list directly after this one with - * a reduced time so we'll ask the driver to execute - * it right after finishing the previous one, in the - * hope that it'll also be executed right afterwards, - * effectively extending the old one. - * If there's no minimum time left, just add it to the - * normal list. - * TODO: the ROC type is ignored here, assuming that it - * is better to immediately use the current ROC. + * check if it fits entirely within the existing one, + * in which case it will just be dependent as well. + * Otherwise, schedule it by itself. */ if (!tmp->hw_begun) { list_add_tail(&roc->list, &tmp->dependents); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ab46ab4a7249..c0a9187bc3a9 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -205,6 +205,8 @@ enum ieee80211_packet_rx_flags { * @IEEE80211_RX_CMNTR: received on cooked monitor already * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported * to cfg80211_report_obss_beacon(). + * @IEEE80211_RX_REORDER_TIMER: this frame is released by the + * reorder buffer timeout timer, not the normal RX path * * These flags are used across handling multiple interfaces * for a single frame. @@ -212,6 +214,7 @@ enum ieee80211_packet_rx_flags { enum ieee80211_rx_flags { IEEE80211_RX_CMNTR = BIT(0), IEEE80211_RX_BEACON_REPORTED = BIT(1), + IEEE80211_RX_REORDER_TIMER = BIT(2), }; struct ieee80211_rx_data { @@ -325,12 +328,6 @@ struct mesh_preq_queue { u8 flags; }; -#if HZ/100 == 0 -#define IEEE80211_ROC_MIN_LEFT 1 -#else -#define IEEE80211_ROC_MIN_LEFT (HZ/100) -#endif - struct ieee80211_roc_work { struct list_head list; struct list_head dependents; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index bab5c63c0bad..84cef600c573 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -522,6 +522,12 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) memcpy(sdata->vif.hw_queue, master->vif.hw_queue, sizeof(sdata->vif.hw_queue)); sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef; + + mutex_lock(&local->key_mtx); + sdata->crypto_tx_tailroom_needed_cnt += + master->crypto_tx_tailroom_needed_cnt; + mutex_unlock(&local->key_mtx); + break; } case NL80211_IFTYPE_AP: diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 2291cd730091..a907f2d5c12d 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -58,6 +58,22 @@ static void assert_key_lock(struct ieee80211_local *local) lockdep_assert_held(&local->key_mtx); } +static void +update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) +{ + struct ieee80211_sub_if_data *vlan; + + if (sdata->vif.type != NL80211_IFTYPE_AP) + return; + + mutex_lock(&sdata->local->mtx); + + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + vlan->crypto_tx_tailroom_needed_cnt += delta; + + mutex_unlock(&sdata->local->mtx); +} + static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) { /* @@ -79,6 +95,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net */ + update_vlan_tailroom_need_count(sdata, 1); + if (!sdata->crypto_tx_tailroom_needed_cnt++) { /* * Flush all XMIT packets currently using HW encryption or no @@ -88,6 +106,15 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) } } +static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata, + int delta) +{ + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta); + + update_vlan_tailroom_need_count(sdata, -delta); + sdata->crypto_tx_tailroom_needed_cnt -= delta; +} + static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; @@ -144,7 +171,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) - sdata->crypto_tx_tailroom_needed_cnt--; + decrease_tailroom_need_count(sdata, 1); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)); @@ -541,7 +568,7 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key, schedule_delayed_work(&sdata->dec_tailroom_needed_wk, HZ/2); } else { - sdata->crypto_tx_tailroom_needed_cnt--; + decrease_tailroom_need_count(sdata, 1); } } @@ -631,6 +658,7 @@ void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom) void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) { struct ieee80211_key *key; + struct ieee80211_sub_if_data *vlan; ASSERT_RTNL(); @@ -639,7 +667,14 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt = 0; + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || + sdata->crypto_tx_tailroom_pending_dec); + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || + vlan->crypto_tx_tailroom_pending_dec); + } list_for_each_entry(key, &sdata->key_list, list) { increment_tailroom_need_count(sdata); @@ -649,6 +684,22 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_unlock(&sdata->local->key_mtx); } +void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_sub_if_data *vlan; + + mutex_lock(&sdata->local->key_mtx); + + sdata->crypto_tx_tailroom_needed_cnt = 0; + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + vlan->crypto_tx_tailroom_needed_cnt = 0; + } + + mutex_unlock(&sdata->local->key_mtx); +} + void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, @@ -688,8 +739,8 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, { struct ieee80211_key *key, *tmp; - sdata->crypto_tx_tailroom_needed_cnt -= - sdata->crypto_tx_tailroom_pending_dec; + decrease_tailroom_need_count(sdata, + sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); @@ -709,6 +760,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *vlan; + struct ieee80211_sub_if_data *master; struct ieee80211_key *key, *tmp; LIST_HEAD(keys); @@ -728,8 +780,20 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, list_for_each_entry_safe(key, tmp, &keys, list) __ieee80211_key_destroy(key, false); - WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || - sdata->crypto_tx_tailroom_pending_dec); + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (sdata->bss) { + master = container_of(sdata->bss, + struct ieee80211_sub_if_data, + u.ap); + + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt != + master->crypto_tx_tailroom_needed_cnt); + } + } else { + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || + sdata->crypto_tx_tailroom_pending_dec); + } + if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || @@ -793,8 +857,8 @@ void ieee80211_delayed_tailroom_dec(struct work_struct *wk) */ mutex_lock(&sdata->local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt -= - sdata->crypto_tx_tailroom_pending_dec; + decrease_tailroom_need_count(sdata, + sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; mutex_unlock(&sdata->local->key_mtx); } diff --git a/net/mac80211/key.h b/net/mac80211/key.h index c5a31835be0e..96557dd1e77d 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -161,6 +161,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta); void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata); +void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata); #define key_mtx_dereference(local, ref) \ rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx))) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 260eed45b6d2..5793f75c5ffd 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2121,7 +2121,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->local->napi) + if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) && + rx->local->napi) napi_gro_receive(rx->local->napi, skb); else netif_receive_skb(skb); @@ -3231,7 +3232,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .flags = 0, + .flags = IEEE80211_RX_REORDER_TIMER, }; struct tid_ampdu_rx *tid_agg_rx; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 79412f16b61d..b864ebc6ab8f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2023,6 +2023,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* add back keys */ list_for_each_entry(sdata, &local->interfaces, list) + ieee80211_reset_crypto_tx_tailroom(sdata); + + list_for_each_entry(sdata, &local->interfaces, list) if (ieee80211_sdata_running(sdata)) ieee80211_enable_keys(sdata); diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index a4220e92f0cc..efa3f48f1ec5 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); - if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN || - skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) + if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) return NULL; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -167,6 +166,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, size_t len; u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; + if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN)) + return -1; + iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); if (!iv) return -1; diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 5b2be12832e6..985e9394e2af 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -17,8 +17,9 @@ #include <linux/err.h> #include <linux/bug.h> #include <linux/completion.h> +#include <linux/crypto.h> #include <linux/ieee802154.h> -#include <crypto/algapi.h> +#include <crypto/aead.h> #include "ieee802154_i.h" #include "llsec.h" @@ -649,7 +650,7 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, u8 iv[16]; unsigned char *data; int authlen, assoclen, datalen, rc; - struct scatterlist src, assoc[2], dst[2]; + struct scatterlist sg; struct aead_request *req; authlen = ieee802154_sechdr_authtag_len(&hdr->sec); @@ -659,30 +660,23 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, if (!req) return -ENOMEM; - sg_init_table(assoc, 2); - sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len); assoclen = skb->mac_len; data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; - if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) { - sg_set_buf(&assoc[1], data, 0); - } else { - sg_set_buf(&assoc[1], data, datalen); + skb_put(skb, authlen); + + sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen + authlen); + + if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) { assoclen += datalen; datalen = 0; } - sg_init_one(&src, data, datalen); - - sg_init_table(dst, 2); - sg_set_buf(&dst[0], data, datalen); - sg_set_buf(&dst[1], skb_put(skb, authlen), authlen); - aead_request_set_callback(req, 0, NULL, NULL); - aead_request_set_assoc(req, assoc, assoclen); - aead_request_set_crypt(req, &src, dst, datalen, iv); + aead_request_set_crypt(req, &sg, &sg, datalen, iv); + aead_request_set_ad(req, assoclen); rc = crypto_aead_encrypt(req); @@ -858,7 +852,7 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, u8 iv[16]; unsigned char *data; int authlen, datalen, assoclen, rc; - struct scatterlist src, assoc[2]; + struct scatterlist sg; struct aead_request *req; authlen = ieee802154_sechdr_authtag_len(&hdr->sec); @@ -868,27 +862,21 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, if (!req) return -ENOMEM; - sg_init_table(assoc, 2); - sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len); assoclen = skb->mac_len; data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; - if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) { - sg_set_buf(&assoc[1], data, 0); - } else { - sg_set_buf(&assoc[1], data, datalen - authlen); + sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen); + + if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) { assoclen += datalen - authlen; - data += datalen - authlen; datalen = authlen; } - sg_init_one(&src, data, datalen); - aead_request_set_callback(req, 0, NULL, NULL); - aead_request_set_assoc(req, assoc, assoclen); - aead_request_set_crypt(req, &src, &src, datalen, iv); + aead_request_set_crypt(req, &sg, &sg, datalen, iv); + aead_request_set_ad(req, assoclen); rc = crypto_aead_decrypt(req); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7b3f732269e4..1f93a5978f2a 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -541,7 +541,7 @@ static void mpls_ifdown(struct net_device *dev) RCU_INIT_POINTER(dev->mpls_ptr, NULL); - kfree(mdev); + kfree_rcu(mdev, rcu); } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, @@ -564,6 +564,17 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, case NETDEV_UNREGISTER: mpls_ifdown(dev); break; + case NETDEV_CHANGENAME: + mdev = mpls_dev_get(dev); + if (mdev) { + int err; + + mpls_dev_sysctl_unregister(mdev); + err = mpls_dev_sysctl_register(dev, mdev); + if (err) + return notifier_from_errno(err); + } + break; } return NOTIFY_OK; } diff --git a/net/mpls/internal.h b/net/mpls/internal.h index b064c345042c..8cabeb5a1cb9 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -16,6 +16,7 @@ struct mpls_dev { int input_enabled; struct ctl_table_header *sysctl; + struct rcu_head rcu; }; struct sk_buff; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f70e34a68f70..a0f3e6a3c7d1 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -863,6 +863,7 @@ config NETFILTER_XT_TARGET_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on (IPV6 || IPV6=n) + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES @@ -1356,6 +1357,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK depends on (IPV6 || IPV6=n) + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 49532672f66d..285eae3a1454 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3823,6 +3823,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); ip_vs_stop_estimator(net, &ipvs->tot_stats); + + if (!net_eq(net, &init_net)) + kfree(ipvs->sysctl_tbl); } #else diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 5caa0c41bf26..70383de72054 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -202,7 +202,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW - * sLA -> sTW Last ACK detected. + * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ @@ -261,7 +261,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW - * sLA -> sTW Last ACK detected. + * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ @@ -906,6 +906,7 @@ static int tcp_packet(struct nf_conn *ct, 1 : ct->proto.tcp.last_win; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale = ct->proto.tcp.last_wscale; + ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = ct->proto.tcp.last_flags; memset(&ct->proto.tcp.seen[dir], 0, @@ -923,7 +924,9 @@ static int tcp_packet(struct nf_conn *ct, * may be in sync but we are not. In that case, we annotate * the TCP options and let the packet go through. If it is a * valid SYN packet, the server will reply with a SYN/ACK, and - * then we'll get in sync. Otherwise, the server ignores it. */ + * then we'll get in sync. Otherwise, the server potentially + * responds with a challenge ACK if implementing RFC5961. + */ if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) { struct ip_ct_tcp_state seen = {}; @@ -939,6 +942,13 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_SACK_PERM; } + /* Mark the potential for RFC5961 challenge ACK, + * this pose a special problem for LAST_ACK state + * as ACK is intrepretated as ACKing last FIN. + */ + if (old_state == TCP_CONNTRACK_LAST_ACK) + ct->proto.tcp.last_flags |= + IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) @@ -970,6 +980,25 @@ static int tcp_packet(struct nf_conn *ct, nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid state "); return -NF_ACCEPT; + case TCP_CONNTRACK_TIME_WAIT: + /* RFC5961 compliance cause stack to send "challenge-ACK" + * e.g. in response to spurious SYNs. Conntrack MUST + * not believe this ACK is acking last FIN. + */ + if (old_state == TCP_CONNTRACK_LAST_ACK && + index == TCP_ACK_SET && + ct->proto.tcp.last_dir != dir && + ct->proto.tcp.last_index == TCP_SYN_SET && + (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) { + /* Detected RFC5961 challenge ACK */ + ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; + spin_unlock_bh(&ct->lock); + if (LOG_INVALID(net, IPPROTO_TCP)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_tcp: challenge-ACK ignored "); + return NF_ACCEPT; /* Don't change state */ + } + break; case TCP_CONNTRACK_CLOSE: if (index == TCP_RST_SET && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ad9d11fb29fd..34ded09317e7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4472,9 +4472,9 @@ EXPORT_SYMBOL_GPL(nft_data_init); */ void nft_data_uninit(const struct nft_data *data, enum nft_data_types type) { - switch (type) { - case NFT_DATA_VALUE: + if (type < NFT_DATA_VERDICT) return; + switch (type) { case NFT_DATA_VERDICT: return nft_verdict_uninit(data); default: diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3ad91266c821..4ef1fae8445e 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1073,7 +1073,13 @@ static struct pernet_operations nfnl_log_net_ops = { static int __init nfnetlink_log_init(void) { - int status = -ENOMEM; + int status; + + status = register_pernet_subsys(&nfnl_log_net_ops); + if (status < 0) { + pr_err("failed to register pernet ops\n"); + goto out; + } netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); @@ -1088,28 +1094,23 @@ static int __init nfnetlink_log_init(void) goto cleanup_subsys; } - status = register_pernet_subsys(&nfnl_log_net_ops); - if (status < 0) { - pr_err("failed to register pernet ops\n"); - goto cleanup_logger; - } return status; -cleanup_logger: - nf_log_unregister(&nfulnl_logger); cleanup_subsys: nfnetlink_subsys_unregister(&nfulnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_log_net_ops); +out: return status; } static void __exit nfnetlink_log_fini(void) { - unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_log_net_ops); } MODULE_DESCRIPTION("netfilter userspace logging"); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 0b98c7420239..11c7682fa0ea 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1317,7 +1317,13 @@ static struct pernet_operations nfnl_queue_net_ops = { static int __init nfnetlink_queue_init(void) { - int status = -ENOMEM; + int status; + + status = register_pernet_subsys(&nfnl_queue_net_ops); + if (status < 0) { + pr_err("nf_queue: failed to register pernet ops\n"); + goto out; + } netlink_register_notifier(&nfqnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfqnl_subsys); @@ -1326,19 +1332,13 @@ static int __init nfnetlink_queue_init(void) goto cleanup_netlink_notifier; } - status = register_pernet_subsys(&nfnl_queue_net_ops); - if (status < 0) { - pr_err("nf_queue: failed to register pernet ops\n"); - goto cleanup_subsys; - } register_netdevice_notifier(&nfqnl_dev_notifier); nf_register_queue_handler(&nfqh); return status; -cleanup_subsys: - nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); +out: return status; } @@ -1346,9 +1346,9 @@ static void __exit nfnetlink_queue_fini(void) { nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); - unregister_pernet_subsys(&nfnl_queue_net_ops); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_queue_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index daa0b818174b..bf6e76643f78 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -89,7 +89,7 @@ static inline int netlink_is_kernel(struct sock *sk) return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET; } -struct netlink_table *nl_table; +struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); @@ -1081,6 +1081,7 @@ static int netlink_insert(struct sock *sk, u32 portid) if (err) { if (err == -EEXIST) err = -EADDRINUSE; + nlk_sk(sk)->portid = 0; sock_put(sk); } diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 4776282c6417..33e6d6e2908f 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -125,6 +125,7 @@ static struct vport *netdev_create(const struct vport_parms *parms) if (err) goto error_master_upper_dev_unlink; + dev_disable_lro(netdev_vport->dev); dev_set_promiscuity(netdev_vport->dev, 1); netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH; rtnl_unlock(); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b6ef9a04de06..a75864d93142 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) struct tcf_proto_ops *t; int rc = -ENOENT; + /* Wait for outstanding call_rcu()s, if any, from a + * tcf_proto_ops's destroy() handler. + */ + rcu_barrier(); + write_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { if (t == ops) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index ad9eed70bc8f..73a123daa2cc 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (dev->flags & IFF_UP) dev_deactivate(dev); - if (new && new->ops->attach) { - new->ops->attach(new); - num_q = 0; - } + if (new && new->ops->attach) + goto skip; for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue = dev_ingress_queue(dev); @@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_destroy(old); } +skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) atomic_inc(&new->refcnt); dev->qdisc = new ? : &noop_qdisc; + + if (new && new->ops->attach) + new->ops->attach(new); } else { notify_and_destroy(net, skb, n, classid, old, new); } @@ -1883,13 +1885,10 @@ EXPORT_SYMBOL(tcf_destroy_chain); #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { - struct timespec ts; - - hrtimer_get_res(CLOCK_MONOTONIC, &ts); seq_printf(seq, "%08x %08x %08x %08x\n", (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1), 1000000, - (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts))); + (u32)NSEC_PER_SEC / hrtimer_resolution); return 0; } diff --git a/net/sctp/auth.c b/net/sctp/auth.c index fb7976aee61c..4f15b7d730e1 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -381,13 +381,14 @@ nomem: } -/* Public interface to creat the association shared key. +/* Public interface to create the association shared key. * See code above for the algorithm. */ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp) { struct sctp_auth_bytes *secret; struct sctp_shared_key *ep_key; + struct sctp_chunk *chunk; /* If we don't support AUTH, or peer is not capable * we don't need to do anything. @@ -410,6 +411,14 @@ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp) sctp_auth_key_put(asoc->asoc_shared_key); asoc->asoc_shared_key = secret; + /* Update send queue in case any chunk already in there now + * needs authenticating + */ + list_for_each_entry(chunk, &asoc->outqueue.out_chunk_list, list) { + if (sctp_auth_send_cid(chunk->chunk_hdr->type, asoc)) + chunk->auth = 1; + } + return 0; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 46568b85c333..055453d48668 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -338,7 +338,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, fi, tos, type, nlflags, tb_id); if (!err) - fi->fib_flags |= RTNH_F_EXTERNAL; + fi->fib_flags |= RTNH_F_OFFLOAD; } return err; @@ -364,7 +364,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, const struct swdev_ops *ops; int err = 0; - if (!(fi->fib_flags & RTNH_F_EXTERNAL)) + if (!(fi->fib_flags & RTNH_F_OFFLOAD)) return 0; dev = netdev_switch_get_dev_by_nhs(fi); @@ -376,7 +376,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, fi, tos, type, tb_id); if (!err) - fi->fib_flags &= ~RTNH_F_EXTERNAL; + fi->fib_flags &= ~RTNH_F_OFFLOAD; } return err; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 9074b5cede38..f485600c4507 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2142,11 +2142,17 @@ static void tipc_sk_timeout(unsigned long data) peer_node = tsk_peer_node(tsk); if (tsk->probing_state == TIPC_CONN_PROBING) { - /* Previous probe not answered -> self abort */ - skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, - TIPC_CONN_MSG, SHORT_H_SIZE, 0, - own_node, peer_node, tsk->portid, - peer_port, TIPC_ERR_NO_PORT); + if (!sock_owned_by_user(sk)) { + sk->sk_socket->state = SS_DISCONNECTING; + tsk->connected = 0; + tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk), + tsk_peer_port(tsk)); + sk->sk_state_change(sk); + } else { + /* Try again later */ + sk_reset_timer(sk, &sk->sk_timer, (HZ / 20)); + } + } else { skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0, peer_node, own_node, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5266ea7b922b..06430598cf51 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1880,6 +1880,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, unix_state_unlock(sk); timeo = freezable_schedule_timeout(timeo); unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -1939,6 +1943,10 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, struct sk_buff *skb, *last; unix_state_lock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } last = skb = skb_peek(&sk->sk_receive_queue); again: if (skb == NULL) { diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index fff1bef6ed6d..fd682832a0e3 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1333,6 +1333,8 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); wdev_unlock(wdev); + memset(&sinfo, 0, sizeof(sinfo)); + if (rdev_get_station(rdev, dev, bssid, &sinfo)) return NULL; diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 12e82a5e4ad5..42f7c76cf853 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -31,6 +31,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqniv", .icv_truncbits = 64, } }, @@ -49,6 +50,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqniv", .icv_truncbits = 96, } }, @@ -67,6 +69,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqniv", .icv_truncbits = 128, } }, @@ -85,6 +88,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqniv", .icv_truncbits = 64, } }, @@ -103,6 +107,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqniv", .icv_truncbits = 96, } }, @@ -121,6 +126,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqniv", .icv_truncbits = 128, } }, @@ -139,6 +145,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { + .geniv = "seqiv", .icv_truncbits = 128, } }, @@ -152,6 +159,18 @@ static struct xfrm_algo_desc aead_list[] = { .sadb_alg_maxbits = 256 } }, +{ + .name = "rfc7539esp(chacha20,poly1305)", + + .uinfo = { + .aead = { + .geniv = "seqniv", + .icv_truncbits = 128, + } + }, + + .pfkey_supported = 0, +}, }; static struct xfrm_algo_desc aalg_list[] = { @@ -353,6 +372,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 64, .defkeybits = 64, } @@ -373,6 +393,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 64, .defkeybits = 192, } @@ -393,6 +414,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 64, .defkeybits = 128, } @@ -413,6 +435,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 64, .defkeybits = 128, } @@ -433,6 +456,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 128, .defkeybits = 128, } @@ -453,6 +477,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 128, .defkeybits = 128, } @@ -473,6 +498,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 128, .defkeybits = 128, } @@ -493,6 +519,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "echainiv", .blockbits = 128, .defkeybits = 128, } @@ -512,6 +539,7 @@ static struct xfrm_algo_desc ealg_list[] = { .uinfo = { .encr = { + .geniv = "seqiv", .blockbits = 128, .defkeybits = 160, /* 128-bit key + 32-bit nonce */ } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 526c4feb3b50..b58286ecd156 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -13,6 +13,8 @@ #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> +#include <net/ip_tunnels.h> +#include <net/ip6_tunnel.h> static struct kmem_cache *secpath_cachep __read_mostly; @@ -186,6 +188,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) struct xfrm_state *x = NULL; xfrm_address_t *daddr; struct xfrm_mode *inner_mode; + u32 mark = skb->mark; unsigned int family; int decaps = 0; int async = 0; @@ -203,6 +206,18 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SPI_SKB_CB(skb)->daddroff); family = XFRM_SPI_SKB_CB(skb)->family; + /* if tunnel is present override skb->mark value with tunnel i_key */ + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) { + switch (family) { + case AF_INET: + mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); + break; + case AF_INET6: + mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); + break; + } + } + /* Allocate new secpath or COW existing one. */ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { struct sec_path *sp; @@ -229,7 +244,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family); + x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index dab57daae408..4fd725a0c500 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -99,6 +99,7 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq; + XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(x->replay.oseq == 0)) { x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); @@ -177,6 +178,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq; + XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(replay_esn->oseq == 0)) { replay_esn->oseq--; xfrm_audit_state_replay_overflow(x, skb); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f5e39e35d73a..96688cd0f6f1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -927,8 +927,8 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, x->id.spi != spi) continue; - spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_hold(x); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2091664295ba..bd16c6c7e1e7 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -289,6 +289,31 @@ static int attach_one_algo(struct xfrm_algo **algpp, u8 *props, return 0; } +static int attach_crypt(struct xfrm_state *x, struct nlattr *rta) +{ + struct xfrm_algo *p, *ualg; + struct xfrm_algo_desc *algo; + + if (!rta) + return 0; + + ualg = nla_data(rta); + + algo = xfrm_ealg_get_byname(ualg->alg_name, 1); + if (!algo) + return -ENOSYS; + x->props.ealgo = algo->desc.sadb_alg_id; + + p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL); + if (!p) + return -ENOMEM; + + strcpy(p->alg_name, algo->name); + x->ealg = p; + x->geniv = algo->uinfo.encr.geniv; + return 0; +} + static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props, struct nlattr *rta) { @@ -349,8 +374,7 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props, return 0; } -static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props, - struct nlattr *rta) +static int attach_aead(struct xfrm_state *x, struct nlattr *rta) { struct xfrm_algo_aead *p, *ualg; struct xfrm_algo_desc *algo; @@ -363,14 +387,15 @@ static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props, algo = xfrm_aead_get_byname(ualg->alg_name, ualg->alg_icv_len, 1); if (!algo) return -ENOSYS; - *props = algo->desc.sadb_alg_id; + x->props.ealgo = algo->desc.sadb_alg_id; p = kmemdup(ualg, aead_len(ualg), GFP_KERNEL); if (!p) return -ENOMEM; strcpy(p->alg_name, algo->name); - *algpp = p; + x->aead = p; + x->geniv = algo->uinfo.aead.geniv; return 0; } @@ -515,8 +540,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_EXTRA_FLAGS]) x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); - if ((err = attach_aead(&x->aead, &x->props.ealgo, - attrs[XFRMA_ALG_AEAD]))) + if ((err = attach_aead(x, attrs[XFRMA_ALG_AEAD]))) goto error; if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo, attrs[XFRMA_ALG_AUTH_TRUNC]))) @@ -526,9 +550,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, attrs[XFRMA_ALG_AUTH]))) goto error; } - if ((err = attach_one_algo(&x->ealg, &x->props.ealgo, - xfrm_ealg_get_byname, - attrs[XFRMA_ALG_CRYPT]))) + if ((err = attach_crypt(x, attrs[XFRMA_ALG_CRYPT]))) goto error; if ((err = attach_one_algo(&x->calg, &x->props.calgo, xfrm_calg_get_byname, |