diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-05 22:31:59 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-05 22:31:59 +0300 |
| commit | 5518b69b76680a4f2df96b1deca260059db0c2de (patch) | |
| tree | f33cd1519c8efb4590500f2f9617400be233238c /net/ipv6 | |
| parent | 8ad06e56dcbc1984ef0ff8f6e3c19982c5809f73 (diff) | |
| parent | 0e72582270c07850b92cac351c8b97d4f9c123b9 (diff) | |
| download | linux-5518b69b76680a4f2df96b1deca260059db0c2de.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Reasonably busy this cycle, but perhaps not as busy as in the 4.12
merge window:
1) Several optimizations for UDP processing under high load from
Paolo Abeni.
2) Support pacing internally in TCP when using the sch_fq packet
scheduler for this is not practical. From Eric Dumazet.
3) Support mutliple filter chains per qdisc, from Jiri Pirko.
4) Move to 1ms TCP timestamp clock, from Eric Dumazet.
5) Add batch dequeueing to vhost_net, from Jason Wang.
6) Flesh out more completely SCTP checksum offload support, from
Davide Caratti.
7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
Neira Ayuso, and Matthias Schiffer.
8) Add devlink support to nfp driver, from Simon Horman.
9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
Prabhu.
10) Add stack depth tracking to BPF verifier and use this information
in the various eBPF JITs. From Alexei Starovoitov.
11) Support XDP on qed device VFs, from Yuval Mintz.
12) Introduce BPF PROG ID for better introspection of installed BPF
programs. From Martin KaFai Lau.
13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.
14) For loads, allow narrower accesses in bpf verifier checking, from
Yonghong Song.
15) Support MIPS in the BPF selftests and samples infrastructure, the
MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
Daney.
16) Support kernel based TLS, from Dave Watson and others.
17) Remove completely DST garbage collection, from Wei Wang.
18) Allow installing TCP MD5 rules using prefixes, from Ivan
Delalande.
19) Add XDP support to Intel i40e driver, from Björn Töpel
20) Add support for TC flower offload in nfp driver, from Simon
Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
Kicinski, and Bert van Leeuwen.
21) IPSEC offloading support in mlx5, from Ilan Tayari.
22) Add HW PTP support to macb driver, from Rafal Ozieblo.
23) Networking refcount_t conversions, From Elena Reshetova.
24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
for tuning the TCP sockopt settings of a group of applications,
currently via CGROUPs"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
cxgb4: Support for get_ts_info ethtool method
cxgb4: Add PTP Hardware Clock (PHC) support
cxgb4: time stamping interface for PTP
nfp: default to chained metadata prepend format
nfp: remove legacy MAC address lookup
nfp: improve order of interfaces in breakout mode
net: macb: remove extraneous return when MACB_EXT_DESC is defined
bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
bpf: fix return in load_bpf_file
mpls: fix rtm policy in mpls_getroute
net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
...
Diffstat (limited to 'net/ipv6')
33 files changed, 476 insertions, 332 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1d2dbace42ff..3c46e9513a31 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -426,7 +426,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } /* One reference from device. */ - in6_dev_hold(ndev); + refcount_set(&ndev->refcnt, 1); if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; @@ -963,6 +963,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; + struct in6_validator_info i6vi; unsigned int hash; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -974,6 +975,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, return ERR_PTR(-EADDRNOTAVAIL); rcu_read_lock_bh(); + + in6_dev_hold(idev); + if (idev->dead) { err = -ENODEV; /*XXX*/ goto out2; @@ -984,6 +988,17 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out2; } + i6vi.i6vi_addr = *addr; + i6vi.i6vi_dev = idev; + rcu_read_unlock_bh(); + + err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); + + rcu_read_lock_bh(); + err = notifier_to_errno(err); + if (err) + goto out2; + spin_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ @@ -1034,9 +1049,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->rt = rt; ifa->idev = idev; - in6_dev_hold(idev); /* For caller */ - in6_ifa_hold(ifa); + refcount_set(&ifa->refcnt, 1); /* Add to big hash table */ hash = inet6_addr_hash(addr); @@ -1062,6 +1076,7 @@ out2: inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); + in6_dev_put(idev); ifa = ERR_PTR(err); } @@ -1912,15 +1927,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (dad_failed) ifp->flags |= IFA_F_DADFAILED; - if (ifp->flags&IFA_F_PERMANENT) { - spin_lock_bh(&ifp->lock); - addrconf_del_dad_work(ifp); - ifp->flags |= IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); - if (dad_failed) - ipv6_ifa_notify(0, ifp); - in6_ifa_put(ifp); - } else if (ifp->flags&IFA_F_TEMPORARY) { + if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); ifpub = ifp->ifpub; @@ -1933,6 +1940,14 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); + } else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) { + spin_lock_bh(&ifp->lock); + addrconf_del_dad_work(ifp); + ifp->flags |= IFA_F_TENTATIVE; + spin_unlock_bh(&ifp->lock); + if (dad_failed) + ipv6_ifa_notify(0, ifp); + in6_ifa_put(ifp); } else { ipv6_del_addr(ifp); } @@ -2280,7 +2295,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, cfg.fc_flags |= RTF_NONEXTHOP; #endif - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } @@ -2335,7 +2350,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -5562,8 +5577,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) ip6_del_rt(rt); } if (ifp->rt) { - dst_hold(&ifp->rt->dst); - ip6_del_rt(ifp->rt); + if (dst_hold_safe(&ifp->rt->dst)) + ip6_del_rt(ifp->rt); } rt_genid_bump_ipv6(net); break; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index bfa941fc1165..9e3488d50b15 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -88,6 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); +static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { @@ -107,6 +108,24 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_notifier_call_chain); +int register_inet6addr_validator_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_validator_notifier); + +int unregister_inet6addr_validator_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); + +int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); + static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, struct dst_entry **u2, struct flowi6 *u3) diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 07cd7d248bb6..7a428f65c7ec 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -18,6 +18,7 @@ #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> +#include <linux/refcount.h> #if 0 #define ADDRLABEL(x...) printk(x) @@ -36,7 +37,7 @@ struct ip6addrlbl_entry { int addrtype; u32 label; struct hlist_node list; - atomic_t refcnt; + refcount_t refcnt; struct rcu_head rcu; }; @@ -137,12 +138,12 @@ static void ip6addrlbl_free_rcu(struct rcu_head *h) static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) { - return atomic_inc_not_zero(&p->refcnt); + return refcount_inc_not_zero(&p->refcnt); } static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) { - if (atomic_dec_and_test(&p->refcnt)) + if (refcount_dec_and_test(&p->refcnt)) call_rcu(&p->rcu, ip6addrlbl_free_rcu); } @@ -236,7 +237,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->label = label; INIT_HLIST_NODE(&newp->list); write_pnet(&newp->lbl_net, net); - atomic_set(&newp->refcnt, 1); + refcount_set(&newp->refcnt, 1); return newp; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index dda6035e3b84..7802b72196f3 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -25,6 +25,7 @@ #define pr_fmt(fmt) "IPv6: " fmt +#include <crypto/algapi.h> #include <crypto/hash.h> #include <linux/module.h> #include <linux/slab.h> @@ -423,7 +424,9 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -481,7 +484,7 @@ static void ah6_input_done(struct crypto_async_request *base, int err) auth_data = ah_tmp_auth(work_iph, hdr_len); icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out; @@ -606,7 +609,9 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) ip6h->hop_limit = 0; sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -627,7 +632,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) goto out_free; } - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out_free; diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 514ac259f543..0bbab8a4b5d8 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -203,12 +203,12 @@ void ipv6_sock_ac_close(struct sock *sk) static void aca_get(struct ifacaddr6 *aca) { - atomic_inc(&aca->aca_refcnt); + refcount_inc(&aca->aca_refcnt); } static void aca_put(struct ifacaddr6 *ac) { - if (atomic_dec_and_test(&ac->aca_refcnt)) { + if (refcount_dec_and_test(&ac->aca_refcnt)) { in6_dev_put(ac->aca_idev); dst_release(&ac->aca_rt->dst); kfree(ac); @@ -232,7 +232,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; - atomic_set(&aca->aca_refcnt, 1); + refcount_set(&aca->aca_refcnt, 1); return aca; } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 8d772fea1dde..1323b9679cf7 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -227,7 +227,7 @@ static int calipso_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - atomic_inc(&entry->lsm_data->refcount); + refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CALIPSO; @@ -296,7 +296,7 @@ static int calipso_cache_add(const unsigned char *calipso_ptr, } entry->key_len = calipso_ptr_len; entry->hash = calipso_map_cache_hash(calipso_ptr, calipso_ptr_len); - atomic_inc(&secattr->cache->refcount); + refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CALIPSO_CACHE_BUCKETS - 1); @@ -338,7 +338,7 @@ static struct calipso_doi *calipso_doi_search(u32 doi) struct calipso_doi *iter; list_for_each_entry_rcu(iter, &calipso_doi_list, list) - if (iter->doi == doi && atomic_read(&iter->refcount)) + if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } @@ -370,7 +370,7 @@ static int calipso_doi_add(struct calipso_doi *doi_def, if (doi_def->doi == CALIPSO_DOI_UNKNOWN) goto doi_add_return; - atomic_set(&doi_def->refcount, 1); + refcount_set(&doi_def->refcount, 1); spin_lock(&calipso_doi_list_lock); if (calipso_doi_search(doi_def->doi)) { @@ -458,7 +458,7 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!atomic_dec_and_test(&doi_def->refcount)) { + if (!refcount_dec_and_test(&doi_def->refcount)) { spin_unlock(&calipso_doi_list_lock); ret_val = -EBUSY; goto doi_remove_return; @@ -499,7 +499,7 @@ static struct calipso_doi *calipso_doi_getdef(u32 doi) doi_def = calipso_doi_search(doi); if (!doi_def) goto doi_getdef_return; - if (!atomic_inc_not_zero(&doi_def->refcount)) + if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: @@ -520,7 +520,7 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!doi_def) return; - if (!atomic_dec_and_test(&doi_def->refcount)) + if (!refcount_dec_and_test(&doi_def->refcount)) return; spin_lock(&calipso_doi_list_lock); list_del_rcu(&doi_def->list); @@ -553,7 +553,7 @@ static int calipso_doi_walk(u32 *skip_cnt, rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &calipso_doi_list, list) - if (atomic_read(&iter_doi->refcount) > 0) { + if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5c786f5ab961..a1f918713006 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -1041,6 +1041,6 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 1fe99ba8066c..9ed35473dcb5 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -118,7 +118,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, static void esp_ssg_unref(struct xfrm_state *x, void *tmp) { - __be32 *seqhi; struct crypto_aead *aead = x->data; int seqhilen = 0; u8 *iv; @@ -128,7 +127,6 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) if (x->props.flags & XFRM_STATE_ESN) seqhilen += sizeof(__be32); - seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); @@ -224,12 +222,9 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info u8 *vaddr; int nfrags; struct page *page; - struct ip_esp_hdr *esph; struct sk_buff *trailer; int tailen = esp->tailen; - esph = ip_esp_hdr(skb); - if (!skb_cloned(skb)) { if (tailen <= skb_availroom(skb)) { nfrags = 1; @@ -280,7 +275,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->data_len += tailen; skb->truesize += tailen; if (sk) - atomic_add(tailen, &sk->sk_wmem_alloc); + refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } @@ -346,9 +341,11 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info esph = esp_output_set_esn(skb, x, ip_esp_hdr(skb), seqhi); sg_init_table(sg, esp->nfrags); - skb_to_sgvec(skb, sg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, sg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; if (!esp->inplace) { int allocsize; @@ -372,9 +369,11 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info spin_unlock_bh(&x->lock); sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1); - skb_to_sgvec(skb, dsg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, dsg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; } if ((x->props.flags & XFRM_STATE_ESN)) @@ -534,7 +533,7 @@ static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = (void *)skb_push(skb, 4); + esph = skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; @@ -618,7 +617,9 @@ skip_cow: esp_input_set_header(skb, seqhi); sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + ret = skb_to_sgvec(skb, sg, 0, skb->len); + if (unlikely(ret < 0)) + goto out; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index b636f1da9aec..4996d734f1d2 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -847,7 +847,7 @@ static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto, ihdr = (struct rt0_hdr *) opt; - phdr = (struct rt0_hdr *) skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); + phdr = skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); memcpy(phdr, ihdr, sizeof(struct rt0_hdr)); hops = ihdr->rt_hdr.hdrlen >> 1; @@ -873,7 +873,7 @@ static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto, sr_ihdr = (struct ipv6_sr_hdr *)opt; plen = (sr_ihdr->hdrlen + 1) << 3; - sr_phdr = (struct ipv6_sr_hdr *)skb_push(skb, plen); + sr_phdr = skb_push(skb, plen); memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr)); hops = sr_ihdr->first_segment + 1; @@ -923,7 +923,7 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt) { - struct ipv6_opt_hdr *h = (struct ipv6_opt_hdr *)skb_push(skb, ipv6_optlen(opt)); + struct ipv6_opt_hdr *h = skb_push(skb, ipv6_optlen(opt)); memcpy(h, opt, ipv6_optlen(opt)); h->nexthdr = *proto; @@ -971,7 +971,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; - atomic_set(&opt2->refcnt, 1); + refcount_set(&opt2->refcnt, 1); } return opt2; } @@ -1056,7 +1056,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); - atomic_set(&opt2->refcnt, 1); + refcount_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index 9ea249b9451e..6de3c04b0f30 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -14,6 +14,8 @@ #include <net/udp.h> #include <net/udp_tunnel.h> +#if IS_ENABLED(CONFIG_IPV6_FOU_TUNNEL) + static void fou6_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, struct flowi6 *fl6, u8 *protocol, __be16 sport) { @@ -33,8 +35,8 @@ static void fou6_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, *protocol = IPPROTO_UDP; } -int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi6 *fl6) +static int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi6 *fl6) { __be16 sport; int err; @@ -49,10 +51,9 @@ int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, return 0; } -EXPORT_SYMBOL(fou6_build_header); -int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi6 *fl6) +static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi6 *fl6) { __be16 sport; int err; @@ -67,9 +68,6 @@ int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, return 0; } -EXPORT_SYMBOL(gue6_build_header); - -#if IS_ENABLED(CONFIG_IPV6_FOU_TUNNEL) static const struct ip6_tnl_encap_ops fou_ip6tun_ops = { .encap_hlen = fou_encap_hlen, diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index b3df03e3faa0..0c02a09bc351 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -91,7 +91,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) drop: kfree_skb(skb); - return -EINVAL; + return err; } static int ila_input(struct sk_buff *skb) @@ -117,7 +117,8 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { static int ila_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ila_lwt *ilwt; struct ila_params *p; @@ -146,7 +147,7 @@ static int ila_build_state(struct nlattr *nla, return -EINVAL; } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, NULL); + ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); if (ret < 0) return ret; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index d0900918a19e..b13b8f93079d 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -75,7 +75,7 @@ begin: continue; if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) continue; - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { @@ -172,7 +172,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, &refcounted); - if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e6b78ba0e636..5477ba729c36 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -153,11 +153,6 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } -static void rt6_rcu_free(struct rt6_info *rt) -{ - call_rcu(&rt->dst.rcu_head, dst_rcu_free); -} - static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -172,7 +167,8 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); pcpu_rt = *ppcpu_rt; if (pcpu_rt) { - rt6_rcu_free(pcpu_rt); + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); *ppcpu_rt = NULL; } } @@ -185,7 +181,8 @@ static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { rt6_free_pcpu(rt); - rt6_rcu_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } } @@ -472,7 +469,8 @@ out: static struct fib6_node *fib6_add_1(struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, - int replace_required, int sernum) + int replace_required, int sernum, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -496,6 +494,8 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { + NL_SET_ERR_MSG(extack, + "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } @@ -542,6 +542,8 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, * That would keep IPv6 consistent with IPv4 */ if (replace_required) { + NL_SET_ERR_MSG(extack, + "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } @@ -963,7 +965,8 @@ void fib6_force_start_gc(struct net *net) */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc) + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -971,8 +974,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); - if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) && - !atomic_read(&rt->dst.__refcnt))) + if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; if (info->nlh) { @@ -986,7 +988,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum); + replace_required, sernum, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1027,7 +1029,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(sfn, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated @@ -1046,7 +1049,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -1067,7 +1071,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) fib6_prune_clones(info->nl_net, pn); - rt->dst.flags &= ~DST_NOCACHE; } out: @@ -1092,8 +1095,10 @@ out: atomic_inc(&pn->leaf->rt6i_ref); } #endif - if (!(rt->dst.flags & DST_NOCACHE)) - dst_free(&rt->dst); + /* Always release dst as dst->__refcnt is guaranteed + * to be taken before entering this function + */ + dst_release_immediate(&rt->dst); } return err; @@ -1104,8 +1109,10 @@ out: st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); - if (!(rt->dst.flags & DST_NOCACHE)) - dst_free(&rt->dst); + /* Always release dst as dst->__refcnt is guaranteed + * to be taken before entering this function + */ + dst_release_immediate(&rt->dst); return err; #endif } @@ -1774,7 +1781,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) } gc_args->more++; } else if (rt->rt6i_flags & RTF_CACHE) { - if (atomic_read(&rt->dst.__refcnt) == 0 && + if (atomic_read(&rt->dst.__refcnt) == 1 && time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { RT6_TRACE("aging clone %p\n", rt); return -1; @@ -1812,8 +1819,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; - - gc_args.more = icmp6_dst_gc(); + gc_args.more = 0; fib6_clean_all(net, fib6_age, &gc_args); now = jiffies; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 64eea3962733..67ff2aaf5dcb 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -942,7 +942,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, const void *daddr, const void *saddr, unsigned int len) { struct ip6_tnl *t = netdev_priv(dev); - struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); + struct ipv6hdr *ipv6h = skb_push(skb, t->hlen); __be16 *p = (__be16 *)(ipv6h+1); ip6_flow_hdr(ipv6h, 0, @@ -1170,7 +1170,8 @@ static struct pernet_operations ip6gre_net_ops = { .size = sizeof(struct ip6gre_net), }; -static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be16 flags; @@ -1188,7 +1189,8 @@ static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct in6_addr daddr; @@ -1209,7 +1211,7 @@ static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) } out: - return ip6gre_tunnel_validate(tb, data); + return ip6gre_tunnel_validate(tb, data, extack); } @@ -1342,7 +1344,8 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[], } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *nt; struct net *net = dev_net(dev); @@ -1403,7 +1406,8 @@ out: } static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t, *nt = netdev_priv(dev); struct net *net = nt->net; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1699acb2fa2c..1422d6c08377 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -67,9 +67,6 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * struct in6_addr *nexthop; int ret; - skb->protocol = htons(ETH_P_IPV6); - skb->dev = dev; - if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -154,6 +151,9 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + if (unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); @@ -682,7 +682,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb_frag_list_init(skb); __skb_pull(skb, hlen); - fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr)); + fh = __skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); @@ -698,15 +698,13 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); - dst_hold(&rt->dst); - for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); - fh = (struct frag_hdr *)__skb_push(frag, sizeof(struct frag_hdr)); + fh = __skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), tmp_hdr, @@ -742,7 +740,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); - ip6_rt_put(rt); return 0; } @@ -750,7 +747,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); - ip6_rt_put(rt); return err; slow_path_clean: @@ -869,7 +865,6 @@ fail_toobig: if (skb->sk && dst_allfrag(skb_dst(skb))) sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); - skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; @@ -1477,7 +1472,7 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (atomic_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len, 1, @@ -1586,7 +1581,7 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 8c6c3c8e7eef..3a0ba2ae4b0f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1885,7 +1885,8 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) return 0; } -static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; @@ -1974,7 +1975,8 @@ static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[], } static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -2005,7 +2007,8 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 837ea1eefe7f..486c2305f53c 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -907,7 +907,8 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) return 0; } -static int vti6_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vti6_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return 0; } @@ -940,7 +941,8 @@ static void vti6_netlink_parms(struct nlattr *data[], } static int vti6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl *nt; @@ -966,7 +968,8 @@ static void vti6_dellink(struct net_device *dev, struct list_head *head) } static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t; struct __ip6_tnl_parm p; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 2ecb39b943b5..7454850f2098 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -116,6 +116,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, int cmd); +static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr6_table *mrt, bool all); @@ -846,7 +847,8 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct ipv6hdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); @@ -1106,7 +1108,8 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct ipv6hdr)); if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; @@ -1123,8 +1126,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, } /* - * Bounce a cache query up to pim6sd. We could use netlink for this but pim6sd - * expects the following bizarre scheme. + * Bounce a cache query up to pim6sd and netlink. * * Called under mrt_lock. */ @@ -1206,6 +1208,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, return -EINVAL; } + mrt6msg_netlink_event(mrt, skb); + /* * Deliver to user space multicast routing algorithms */ @@ -2455,6 +2459,71 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } +static size_t mrt6msg_netlink_msgsize(size_t payloadlen) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtgenmsg)) + + nla_total_size(1) /* IP6MRA_CREPORT_MSGTYPE */ + + nla_total_size(4) /* IP6MRA_CREPORT_MIF_ID */ + /* IP6MRA_CREPORT_SRC_ADDR */ + + nla_total_size(sizeof(struct in6_addr)) + /* IP6MRA_CREPORT_DST_ADDR */ + + nla_total_size(sizeof(struct in6_addr)) + /* IP6MRA_CREPORT_PKT */ + + nla_total_size(payloadlen) + ; + + return len; +} + +static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt) +{ + struct net *net = read_pnet(&mrt->net); + struct nlmsghdr *nlh; + struct rtgenmsg *rtgenm; + struct mrt6msg *msg; + struct sk_buff *skb; + struct nlattr *nla; + int payloadlen; + + payloadlen = pkt->len - sizeof(struct mrt6msg); + msg = (struct mrt6msg *)skb_transport_header(pkt); + + skb = nlmsg_new(mrt6msg_netlink_msgsize(payloadlen), GFP_ATOMIC); + if (!skb) + goto errout; + + nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, + sizeof(struct rtgenmsg), 0); + if (!nlh) + goto errout; + rtgenm = nlmsg_data(nlh); + rtgenm->rtgen_family = RTNL_FAMILY_IP6MR; + if (nla_put_u8(skb, IP6MRA_CREPORT_MSGTYPE, msg->im6_msgtype) || + nla_put_u32(skb, IP6MRA_CREPORT_MIF_ID, msg->im6_mif) || + nla_put_in6_addr(skb, IP6MRA_CREPORT_SRC_ADDR, + &msg->im6_src) || + nla_put_in6_addr(skb, IP6MRA_CREPORT_DST_ADDR, + &msg->im6_dst)) + goto nla_put_failure; + + nla = nla_reserve(skb, IP6MRA_CREPORT_PKT, payloadlen); + if (!nla || skb_copy_bits(pkt, sizeof(struct mrt6msg), + nla_data(nla), payloadlen)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE_R, NULL, GFP_ATOMIC); + return; + +nla_put_failure: + nlmsg_cancel(skb, nlh); +errout: + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS); +} + static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a531ba032b85..85404e7c3114 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -505,7 +505,7 @@ sticky_done: break; memset(opt, 0, sizeof(*opt)); - atomic_set(&opt->refcnt, 1); + refcount_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; if (copy_from_user(opt+1, optval, optlen)) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 07403fa164e1..12b7c27ce5ce 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -701,7 +701,7 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) spin_lock_bh(&mc->mca_lock); if (del_timer(&mc->mca_timer)) - atomic_dec(&mc->mca_refcnt); + refcount_dec(&mc->mca_refcnt); spin_unlock_bh(&mc->mca_lock); } @@ -819,12 +819,12 @@ static void mld_clear_delrec(struct inet6_dev *idev) static void mca_get(struct ifmcaddr6 *mc) { - atomic_inc(&mc->mca_refcnt); + refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { - if (atomic_dec_and_test(&mc->mca_refcnt)) { + if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree(mc); } @@ -846,7 +846,7 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; - atomic_set(&mc->mca_refcnt, 1); + refcount_set(&mc->mca_refcnt, 1); spin_lock_init(&mc->mca_lock); /* initial mode is (EX, empty) */ @@ -1065,7 +1065,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) return; if (del_timer(&ma->mca_timer)) { - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); delay = ma->mca_timer.expires - jiffies; } @@ -1074,7 +1074,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) - atomic_inc(&ma->mca_refcnt); + refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } @@ -1469,7 +1469,7 @@ int igmp6_event_report(struct sk_buff *skb) if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { spin_lock(&ma->mca_lock); if (del_timer(&ma->mca_timer)) - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER|MAF_TIMER_RUNNING); spin_unlock(&ma->mca_lock); break; @@ -1602,7 +1602,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); - memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); + skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); @@ -1692,7 +1692,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, skb = mld_newpack(pmc->idev, dev->mtu); if (!skb) return NULL; - pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); + pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; @@ -1784,7 +1784,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, } if (!skb) return NULL; - psrc = (struct in6_addr *)skb_put(skb, sizeof(*psrc)); + psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || @@ -2006,10 +2006,9 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); - memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); + skb_put_data(skb, ra, sizeof(ra)); - hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); - memset(hdr, 0, sizeof(struct mld_msg)); + hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; @@ -2392,12 +2391,12 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); delay = ma->mca_timer.expires - jiffies; } if (!mod_timer(&ma->mca_timer, jiffies + delay)) - atomic_inc(&ma->mca_refcnt); + refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; spin_unlock_bh(&ma->mca_lock); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d310dc41209a..0327c1f2e6fc 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -528,7 +528,7 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, if (!skb) return; - msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, @@ -597,7 +597,7 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, if (!skb) return; - msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, @@ -657,7 +657,7 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, if (!skb) return; - msg = (struct rs_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, @@ -1633,7 +1633,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (!buff) goto release; - msg = (struct rd_msg *)skb_put(buff, sizeof(*msg)); + msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index d3c4daa708b9..ce203dd729e0 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -27,7 +27,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, struct ipv6hdr *iph; skb_reset_network_header(skb); - iph = (struct ipv6hdr *)skb_put(skb, sizeof(*iph)); + iph = skb_put(skb, sizeof(*iph)); ip6_flow_hdr(iph, 0, 0); iph->hop_limit = net->ipv6.devconf_all->hop_limit; iph->nexthdr = IPPROTO_TCP; @@ -105,7 +105,7 @@ synproxy_send_client_synack(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->daddr, &iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(__cookie_v6_init_sequence(iph, th, &mss)); @@ -147,7 +147,7 @@ synproxy_send_server_syn(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->saddr, &iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(recv_seq - 1); @@ -192,7 +192,7 @@ synproxy_send_server_ack(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->daddr, &iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(ntohl(th->ack_seq)); @@ -230,7 +230,7 @@ synproxy_send_client_ack(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->saddr, &iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(ntohl(th->seq) + 1); diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 2297c9f073ba..d7b679037bae 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -75,8 +75,8 @@ static int masq_device_event(struct notifier_block *this, struct net *net = dev_net(dev); if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } @@ -99,7 +99,7 @@ static void iterate_cleanup_work(struct work_struct *work) w = container_of(work, struct masq_dev_work, work); index = w->ifindex; - nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + nf_ct_iterate_cleanup_net(w->net, device_cmp, (void *)index, 0, 0); put_net(w->net); kfree(w); @@ -110,12 +110,12 @@ static void iterate_cleanup_work(struct work_struct *work) /* ipv6 inet notifier is an atomic notifier, i.e. we cannot * schedule. * - * Unfortunately, nf_ct_iterate_cleanup can run for a long + * Unfortunately, nf_ct_iterate_cleanup_net can run for a long * time if there are lots of conntracks and the system * handles high softirq load, so it frequently calls cond_resched * while iterating the conntrack table. * - * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * So we defer nf_ct_iterate_cleanup_net walk to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount * of ipv6 addresses being deleted), we also need to add an upper diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index eedee5d108d9..24858402e374 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -95,7 +95,7 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, int needs_ack; skb_reset_transport_header(nskb); - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); + tcph = skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ tcph->doff = sizeof(struct tcphdr)/4; tcph->source = oth->dest; @@ -220,9 +220,6 @@ static bool reject6_csum_ok(struct sk_buff *skb, int hook) __be16 fo; u8 proto; - if (skb->csum_bad) - return false; - if (skb_csum_unnecessary(skb)) return true; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 322bd62e688b..0488a24c2a44 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,6 @@ static void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); - rt->dst.flags |= DST_NOCACHE; rt->rt6i_uncached_list = ul; spin_lock_bh(&ul->lock); @@ -354,7 +353,7 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, - 0, DST_OBSOLETE_FORCE_CHK, flags); + 1, DST_OBSOLETE_FORCE_CHK, flags); if (rt) rt6_info_init(rt); @@ -381,7 +380,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, *p = NULL; } } else { - dst_destroy((struct dst_entry *)rt); + dst_release_immediate(&rt->dst); return NULL; } } @@ -932,20 +931,21 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. - It takes new route entry, the addition fails by any reason the - route is freed. In any case, if caller does not hold it, it may - be destroyed. + * It takes new route entry, the addition fails by any reason the + * route is released. + * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct mx6_config *mxc) + struct mx6_config *mxc, + struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mxc); + err = fib6_add(&table->tb6_root, rt, info, mxc, extack); write_unlock_bh(&table->tb6_lock); return err; @@ -956,7 +956,9 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; struct mx6_config mxc = { .mx = NULL, }; - return __ip6_ins_rt(rt, &info, &mxc); + /* Hold dst to account for the reference from the fib6 tree */ + dst_hold(&rt->dst); + return __ip6_ins_rt(rt, &info, &mxc, NULL); } static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, @@ -1048,7 +1050,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) prev = cmpxchg(p, NULL, pcpu_rt); if (prev) { /* If someone did it before us, return prev instead */ - dst_destroy(&pcpu_rt->dst); + dst_release_immediate(&pcpu_rt->dst); pcpu_rt = prev; } } else { @@ -1058,7 +1060,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) * since rt is going away anyway. The next * dst_check() will trigger a re-lookup. */ - dst_destroy(&pcpu_rt->dst); + dst_release_immediate(&pcpu_rt->dst); pcpu_rt = rt; } dst_hold(&pcpu_rt->dst); @@ -1128,12 +1130,15 @@ redo_rt6_select: uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); dst_release(&rt->dst); - if (uncached_rt) + if (uncached_rt) { + /* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc() + * No need for another dst_hold() + */ rt6_uncached_list_add(uncached_rt); - else + } else { uncached_rt = net->ipv6.ip6_null_entry; - - dst_hold(&uncached_rt->dst); + dst_hold(&uncached_rt->dst); + } trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); return uncached_rt; @@ -1244,9 +1249,11 @@ EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; + struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; - rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1, + DST_OBSOLETE_NONE, 0); if (rt) { rt6_info_init(rt); @@ -1256,10 +1263,8 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); - rt->rt6i_idev = ort->rt6i_idev; - if (rt->rt6i_idev) - in6_dev_hold(rt->rt6i_idev); + rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; rt->rt6i_metric = 0; @@ -1268,8 +1273,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif - - dst_free(new); } dst_release(dst_orig); @@ -1322,7 +1325,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt6_dst_from_metrics_check(rt); if (rt->rt6i_flags & RTF_PCPU || - (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from)) + (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from)) return rt6_dst_from_check(rt, cookie); else return rt6_check(rt, cookie); @@ -1355,8 +1358,8 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { if (rt->rt6i_flags & RTF_CACHE) { - dst_hold(&rt->dst); - ip6_del_rt(rt); + if (dst_hold_safe(&rt->dst)) + ip6_del_rt(rt); } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; } @@ -1420,6 +1423,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, * invalidate the sk->sk_dst_cache. */ ip6_ins_rt(nrt6); + /* Release the reference taken in + * ip6_rt_cache_alloc() + */ + dst_release(&nrt6->dst); } } } @@ -1648,9 +1655,6 @@ out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } -static struct dst_entry *icmp6_dst_gc_list; -static DEFINE_SPINLOCK(icmp6_dst_lock); - struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { @@ -1671,19 +1675,16 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - atomic_set(&rt->dst.__refcnt, 1); rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); - spin_lock_bh(&icmp6_dst_lock); - rt->dst.next = icmp6_dst_gc_list; - icmp6_dst_gc_list = &rt->dst; - spin_unlock_bh(&icmp6_dst_lock); - - fib6_force_start_gc(net); + /* Add this dst into uncached_list so that rt6_ifdown() can + * do proper release of the net_device + */ + rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -1691,48 +1692,6 @@ out: return dst; } -int icmp6_dst_gc(void) -{ - struct dst_entry *dst, **pprev; - int more = 0; - - spin_lock_bh(&icmp6_dst_lock); - pprev = &icmp6_dst_gc_list; - - while ((dst = *pprev) != NULL) { - if (!atomic_read(&dst->__refcnt)) { - *pprev = dst->next; - dst_free(dst); - } else { - pprev = &dst->next; - ++more; - } - } - - spin_unlock_bh(&icmp6_dst_lock); - - return more; -} - -static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), - void *arg) -{ - struct dst_entry *dst, **pprev; - - spin_lock_bh(&icmp6_dst_lock); - pprev = &icmp6_dst_gc_list; - while ((dst = *pprev) != NULL) { - struct rt6_info *rt = (struct rt6_info *) dst; - if (func(rt, arg)) { - *pprev = dst->next; - dst_free(dst); - } else { - pprev = &dst->next; - } - } - spin_unlock_bh(&icmp6_dst_lock); -} - static int ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); @@ -1844,7 +1803,8 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, return rt; } -static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) +static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; @@ -1855,14 +1815,25 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) int err = -EINVAL; /* RTF_PCPU is an internal flag; can not be set by userspace */ - if (cfg->fc_flags & RTF_PCPU) + if (cfg->fc_flags & RTF_PCPU) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto out; + } - if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) + if (cfg->fc_dst_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + goto out; + } + if (cfg->fc_src_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid source address length"); goto out; + } #ifndef CONFIG_IPV6_SUBTREES - if (cfg->fc_src_len) + if (cfg->fc_src_len) { + NL_SET_ERR_MSG(extack, + "Specifying source address requires IPV6_SUBTREES to be enabled"); goto out; + } #endif if (cfg->fc_ifindex) { err = -ENODEV; @@ -1926,7 +1897,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET6, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); @@ -2013,9 +1984,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) err = -EINVAL; if (ipv6_chk_addr_and_flags(net, gw_addr, gwa_type & IPV6_ADDR_LINKLOCAL ? - dev : NULL, 0, 0)) + dev : NULL, 0, 0)) { + NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; - + } rt->rt6i_gateway = *gw_addr; if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -2031,8 +2003,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | - IPV6_ADDR_MAPPED))) + IPV6_ADDR_MAPPED))) { + NL_SET_ERR_MSG(extack, + "Invalid gateway address"); goto out; + } if (cfg->fc_table) { grt = ip6_nh_lookup_table(net, cfg, gw_addr); @@ -2072,8 +2047,14 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) goto out; } err = -EINVAL; - if (!dev || (dev->flags & IFF_LOOPBACK)) + if (!dev) { + NL_SET_ERR_MSG(extack, "Egress device not specified"); goto out; + } else if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG(extack, + "Egress device can not be loopback device for this route"); + goto out; + } } err = -ENODEV; @@ -2082,6 +2063,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) if (!ipv6_addr_any(&cfg->fc_prefsrc)) { if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { + NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out; } @@ -2106,18 +2088,19 @@ out: if (idev) in6_dev_put(idev); if (rt) - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); return ERR_PTR(err); } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct mx6_config mxc = { .mx = NULL, }; struct rt6_info *rt; int err; - rt = ip6_route_info_create(cfg); + rt = ip6_route_info_create(cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -2128,14 +2111,14 @@ int ip6_route_add(struct fib6_config *cfg) if (err) goto out; - err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack); kfree(mxc.mx); return err; out: if (rt) - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); return err; } @@ -2146,8 +2129,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) struct fib6_table *table; struct net *net = dev_net(rt->dst.dev); - if (rt == net->ipv6.ip6_null_entry || - rt->dst.flags & DST_NOCACHE) { + if (rt == net->ipv6.ip6_null_entry) { err = -ENOENT; goto out; } @@ -2222,7 +2204,8 @@ out_put: return err; } -static int ip6_route_del(struct fib6_config *cfg) +static int ip6_route_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_node *fn; @@ -2230,8 +2213,10 @@ static int ip6_route_del(struct fib6_config *cfg) int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); - if (!table) + if (!table) { + NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; + } read_lock_bh(&table->tb6_lock); @@ -2369,7 +2354,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; if (ip6_ins_rt(nrt)) - goto out; + goto out_release; netevent.old = &rt->dst; netevent.new = &nrt->dst; @@ -2382,6 +2367,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu ip6_del_rt(rt); } +out_release: + /* Release the reference taken in + * ip6_rt_cache_alloc() + */ + dst_release(&nrt->dst); + out: neigh_release(neigh); } @@ -2483,7 +2474,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } @@ -2529,7 +2520,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, cfg.fc_gateway = *gwaddr; - if (!ip6_route_add(&cfg)) { + if (!ip6_route_add(&cfg, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); @@ -2622,10 +2613,10 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&cfg); + err = ip6_route_add(&cfg, NULL); break; case SIOCDELRT: - err = ip6_route_del(&cfg); + err = ip6_route_del(&cfg, NULL); break; default: err = -EINVAL; @@ -2729,9 +2720,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_dst.plen = 128; tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; rt->rt6i_table = fib6_get_table(net, tb_id); - rt->dst.flags |= DST_NOCACHE; - - atomic_set(&rt->dst.__refcnt, 1); return rt; } @@ -2819,7 +2807,6 @@ void rt6_ifdown(struct net *net, struct net_device *dev) }; fib6_clean_all(net, fib6_ifdown, &adn); - icmp6_clean_all(fib6_ifdown, &adn); if (dev) rt6_uncached_list_flush_dev(net, dev); } @@ -2904,7 +2891,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, - struct fib6_config *cfg) + struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; @@ -2988,7 +2976,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, - cfg->fc_mp_len); + cfg->fc_mp_len, extack); if (err < 0) goto errout; } @@ -3007,7 +2995,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } @@ -3098,7 +3086,8 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } -static int ip6_route_multipath_add(struct fib6_config *cfg) +static int ip6_route_multipath_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rt6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; @@ -3146,7 +3135,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) r_cfg.fc_encap_type = nla_get_u16(nla); } - rt = ip6_route_info_create(&r_cfg); + rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -3155,7 +3144,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); goto cleanup; } @@ -3171,7 +3160,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { rt_last = nh->rt6_info; - err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc); + err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack); /* save reference to first route for notification */ if (!rt_notif && !err) rt_notif = nh->rt6_info; @@ -3213,13 +3202,13 @@ add_errout: list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; - ip6_route_del(&nh->r_cfg); + ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { if (nh->rt6_info) - dst_free(&nh->rt6_info->dst); + dst_release_immediate(&nh->rt6_info->dst); kfree(nh->mxc.mx); list_del(&nh->next); kfree(nh); @@ -3228,7 +3217,8 @@ cleanup: return err; } -static int ip6_route_multipath_del(struct fib6_config *cfg) +static int ip6_route_multipath_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; @@ -3255,7 +3245,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg) r_cfg.fc_flags |= RTF_GATEWAY; } } - err = ip6_route_del(&r_cfg); + err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; @@ -3271,15 +3261,15 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_del(&cfg); + return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; - return ip6_route_del(&cfg); + return ip6_route_del(&cfg, extack); } } @@ -3289,14 +3279,14 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_add(&cfg); + return ip6_route_multipath_add(&cfg, extack); else - return ip6_route_add(&cfg); + return ip6_route_add(&cfg, extack); } static size_t rt6_nlmsg_size(struct rt6_info *rt) @@ -3577,11 +3567,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; + int err, iif = 0, oif = 0; + struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6; - int err, iif = 0, oif = 0; + bool fibmatch; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); @@ -3592,6 +3584,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, memset(&fl6, 0, sizeof(fl6)); rtm = nlmsg_data(nlh); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0); + fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) @@ -3637,12 +3630,23 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6, - flags); + if (!fibmatch) + dst = ip6_route_input_lookup(net, dev, &fl6, flags); } else { fl6.flowi6_oif = oif; - rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); + if (!fibmatch) + dst = ip6_route_output(net, NULL, &fl6); + } + + if (fibmatch) + dst = ip6_route_lookup(net, &fl6, 0); + + rt = container_of(dst, struct rt6_info, dst); + if (rt->dst.error) { + err = rt->dst.error; + ip6_rt_put(rt); + goto errout; } if (rt == net->ipv6.ip6_null_entry) { @@ -3659,10 +3663,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } skb_dst_set(skb, &rt->dst); - - err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + if (fibmatch) + err = rt6_fill_node(net, skb, rt, NULL, NULL, iif, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + else + err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); if (err < 0) { kfree_skb(skb); goto errout; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 5f44ffed2576..15fba55e3da8 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -303,13 +303,9 @@ static int seg6_genl_dumphmac_done(struct netlink_callback *cb) static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; - struct net *net = sock_net(skb->sk); - struct seg6_pernet_data *sdata; struct seg6_hmac_info *hinfo; int ret; - sdata = seg6_pernet(net); - ret = rhashtable_walk_start(iter); if (ret && ret != -EAGAIN) goto done; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 6a495490d43e..264d772d3c7d 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -326,7 +326,8 @@ drop: static int seg6_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; struct seg6_iptunnel_encap *tuninfo; @@ -336,7 +337,7 @@ static int seg6_build_state(struct nlattr *nla, int err; err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla, - seg6_iptunnel_policy, NULL); + seg6_iptunnel_policy, extack); if (err < 0) return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index f8ad15891cd7..ac912bb21747 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1406,7 +1406,8 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } -static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; @@ -1537,7 +1538,8 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], #endif static int ipip6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip_tunnel *nt; @@ -1573,7 +1575,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5abc3692b901..7b75b0620730 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -162,15 +162,16 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + tsoff = secure_tcpv6_ts_off(sock_net(sk), + ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(&tcp_opt)) + if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) goto out; ret = NULL; @@ -193,7 +194,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); ireq->pktopts = skb; } @@ -211,7 +212,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4f4310a36a04..2521690d62d6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -109,9 +109,9 @@ static u32 tcp_v6_init_seq(const struct sk_buff *skb) tcp_hdr(skb)->source); } -static u32 tcp_v6_init_ts_off(const struct sk_buff *skb) +static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); } @@ -292,7 +292,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); - tp->tsoffset = secure_tcpv6_ts_off(np->saddr.s6_addr32, + tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), + np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); } @@ -514,11 +515,12 @@ static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } -static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, - int optlen) +static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, + char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; + u8 prefixlen; if (optlen < sizeof(cmd)) return -EINVAL; @@ -529,12 +531,22 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (sin6->sin6_family != AF_INET6) return -EINVAL; + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && + prefixlen > 32)) + return -EINVAL; + } else { + prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; + } + if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET); + AF_INET, prefixlen); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6); + AF_INET6, prefixlen); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) @@ -542,10 +554,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + AF_INET, prefixlen, cmd.tcpm_key, + cmd.tcpm_keylen, GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + AF_INET6, prefixlen, cmd.tcpm_key, + cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -720,7 +734,7 @@ static void tcp_v6_init_req(struct request_sock *req, np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || np->repflow)) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); ireq->pktopts = skb; } } @@ -788,7 +802,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); - t1 = (struct tcphdr *) skb_push(buff, tot_len); + t1 = skb_push(buff, tot_len); skb_reset_transport_header(buff); /* Swap the send and the receive. */ @@ -949,7 +963,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); @@ -971,7 +985,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); @@ -1185,7 +1199,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, key->key, key->keylen, + AF_INET6, 128, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } #endif @@ -1248,9 +1262,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (tcp_filter(sk, skb)) - goto discard; - /* * socket locking is here for SMP purposes as backlog rcv * is currently called with bh processing disabled. @@ -1453,6 +1464,8 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); + } else if (tcp_filter(sk, skb)) { + goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); goto discard_and_relse; @@ -1796,7 +1809,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, @@ -1829,7 +1842,7 @@ static void get_timewait6_sock(struct seq_file *seq, dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, - atomic_read(&tw->tw_refcnt), tw); + refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) @@ -1909,6 +1922,7 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 75703fda23e7..4a3e65626e8b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -325,7 +325,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } @@ -362,7 +362,7 @@ try_again: if (!skb) return err; - ulen = skb->len; + ulen = udp_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; @@ -379,14 +379,18 @@ try_again: if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { - checksum_valid = !udp_lib_checksum_complete(skb); + checksum_valid = udp_skb_csum_unnecessary(skb) || + !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } - if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_msg(skb, off, msg, copied); - else { + if (checksum_valid || udp_skb_csum_unnecessary(skb)) { + if (udp_skb_is_linear(skb)) + err = copy_linear_skb(skb, copied, off, &msg->msg_iter); + else + err = skb_copy_datagram_msg(skb, off, msg, copied); + } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; @@ -455,7 +459,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { if (is_udp4) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); @@ -629,6 +634,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } + prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; @@ -910,7 +916,7 @@ static void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; @@ -920,12 +926,11 @@ static void udp_v6_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); if (dst) { - if (dst->flags & DST_NOCACHE) { - if (likely(atomic_inc_not_zero(&dst->__refcnt))) - skb_dst_set(skb, dst); - } else { - skb_dst_set_noref(skb, dst); - } + /* set noref for now. + * any place which wants to hold dst has to call + * dst_hold_safe() + */ + skb_dst_set_noref(skb, dst); } } diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 1e205c3253ac..57fd314ec2b8 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -54,7 +54,7 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); - ph = (struct ip_beet_phdr *)__skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl-hdr_len); + ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index d7b731a78d09..4e438bc7ee87 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -59,7 +59,7 @@ struct xfrm6_tunnel_spi { struct hlist_node list_byspi; xfrm_address_t addr; u32 spi; - atomic_t refcnt; + refcount_t refcnt; struct rcu_head rcu_head; }; @@ -160,7 +160,7 @@ alloc_spi: memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; - atomic_set(&x6spi->refcnt, 1); + refcount_set(&x6spi->refcnt, 1); hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tn->spi_byspi[index]); @@ -178,7 +178,7 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) spin_lock_bh(&xfrm6_tunnel_spi_lock); x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); if (x6spi) { - atomic_inc(&x6spi->refcnt); + refcount_inc(&x6spi->refcnt); spi = x6spi->spi; } else spi = __xfrm6_tunnel_alloc_spi(net, saddr); @@ -207,7 +207,7 @@ static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) list_byaddr) { if (xfrm6_addr_equal(&x6spi->addr, saddr)) { - if (atomic_dec_and_test(&x6spi->refcnt)) { + if (refcount_dec_and_test(&x6spi->refcnt)) { hlist_del_rcu(&x6spi->list_byaddr); hlist_del_rcu(&x6spi->list_byspi); call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); |