summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c120
-rw-r--r--net/ipv6/af_inet6.c3
-rw-r--r--net/ipv6/ah6.c3
-rw-r--r--net/ipv6/esp6.c318
-rw-r--r--net/ipv6/icmp.c68
-rw-r--r--net/ipv6/ila/ila_lwt.c3
-rw-r--r--net/ipv6/inet6_connection_sock.c42
-rw-r--r--net/ipv6/inet6_hashtables.c46
-rw-r--r--net/ipv6/ip6_fib.c3
-rw-r--r--net/ipv6/ip6_gre.c11
-rw-r--r--net/ipv6/ip6_offload.c1
-rw-r--r--net/ipv6/ip6_output.c8
-rw-r--r--net/ipv6/ip6_tunnel.c40
-rw-r--r--net/ipv6/ip6_vti.c6
-rw-r--r--net/ipv6/ip6mr.c13
-rw-r--r--net/ipv6/mcast.c51
-rw-r--r--net/ipv6/netfilter/ip6t_rpfilter.c8
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c3
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c13
-rw-r--r--net/ipv6/route.c87
-rw-r--r--net/ipv6/seg6.c2
-rw-r--r--net/ipv6/seg6_hmac.c48
-rw-r--r--net/ipv6/seg6_iptunnel.c7
-rw-r--r--net/ipv6/syncookies.c41
-rw-r--r--net/ipv6/tcp_ipv6.c20
-rw-r--r--net/ipv6/udp.c29
26 files changed, 604 insertions, 390 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c1e124bc8e1e..156ed578d3c0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -243,6 +243,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.seg6_require_hmac = 0,
#endif
.enhanced_dad = 1,
+ .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -294,6 +295,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.seg6_require_hmac = 0,
#endif
.enhanced_dad = 1,
+ .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64,
};
/* Check if a valid qdisc is available */
@@ -386,9 +388,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
if (ndev->cnf.stable_secret.initialized)
- ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+ ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
else
- ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64;
+ ndev->cnf.addr_gen_mode = ipv6_devconf_dflt.addr_gen_mode;
ndev->cnf.mtu6 = dev->mtu;
ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
@@ -2144,12 +2146,14 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev)
case ARPHRD_SIT:
return addrconf_ifid_sit(eui, dev);
case ARPHRD_IPGRE:
+ case ARPHRD_TUNNEL:
return addrconf_ifid_gre(eui, dev);
case ARPHRD_6LOWPAN:
return addrconf_ifid_eui64(eui, dev);
case ARPHRD_IEEE1394:
return addrconf_ifid_ieee1394(eui, dev);
case ARPHRD_TUNNEL6:
+ case ARPHRD_IP6GRE:
return addrconf_ifid_ip6tnl(eui, dev);
}
return -1;
@@ -2387,8 +2391,8 @@ static void manage_tempaddrs(struct inet6_dev *idev,
static bool is_addr_mode_generate_stable(struct inet6_dev *idev)
{
- return idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY ||
- idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
+ return idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY ||
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
}
int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
@@ -3152,7 +3156,7 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
- switch (idev->addr_gen_mode) {
+ switch (idev->cnf.addr_gen_mode) {
case IN6_ADDR_GEN_MODE_RANDOM:
ipv6_gen_mode_random_init(idev);
/* fallthrough */
@@ -3193,6 +3197,9 @@ static void addrconf_dev_config(struct net_device *dev)
(dev->type != ARPHRD_IEEE1394) &&
(dev->type != ARPHRD_TUNNEL6) &&
(dev->type != ARPHRD_6LOWPAN) &&
+ (dev->type != ARPHRD_IP6GRE) &&
+ (dev->type != ARPHRD_IPGRE) &&
+ (dev->type != ARPHRD_TUNNEL) &&
(dev->type != ARPHRD_NONE)) {
/* Alas, we support only Ethernet autoconfiguration. */
return;
@@ -3204,8 +3211,8 @@ static void addrconf_dev_config(struct net_device *dev)
/* this device type has no EUI support */
if (dev->type == ARPHRD_NONE &&
- idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)
- idev->addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM;
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)
+ idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM;
addrconf_addr_gen(idev, false);
}
@@ -4888,6 +4895,13 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
struct net *net = dev_net(ifa->idev->dev);
int err = -ENOBUFS;
+ /* Don't send DELADDR notification for TENTATIVE address,
+ * since NEWADDR notification is sent only after removing
+ * TENTATIVE flag.
+ */
+ if (ifa->flags & IFA_F_TENTATIVE && event == RTM_DELADDR)
+ return;
+
skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
if (!skb)
goto errout;
@@ -4975,6 +4989,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac;
#endif
array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad;
+ array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode;
}
static inline size_t inet6_ifla6_size(void)
@@ -5086,7 +5101,7 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
if (!nla)
goto nla_put_failure;
- if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode))
+ if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode))
goto nla_put_failure;
read_lock_bh(&idev->lock);
@@ -5204,6 +5219,26 @@ static int inet6_validate_link_af(const struct net_device *dev,
return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy);
}
+static int check_addr_gen_mode(int mode)
+{
+ if (mode != IN6_ADDR_GEN_MODE_EUI64 &&
+ mode != IN6_ADDR_GEN_MODE_NONE &&
+ mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
+ mode != IN6_ADDR_GEN_MODE_RANDOM)
+ return -EINVAL;
+ return 1;
+}
+
+static int check_stable_privacy(struct inet6_dev *idev, struct net *net,
+ int mode)
+{
+ if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
+ !idev->cnf.stable_secret.initialized &&
+ !net->ipv6.devconf_dflt->stable_secret.initialized)
+ return -EINVAL;
+ return 1;
+}
+
static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
{
int err = -EINVAL;
@@ -5225,18 +5260,11 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
if (tb[IFLA_INET6_ADDR_GEN_MODE]) {
u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]);
- if (mode != IN6_ADDR_GEN_MODE_EUI64 &&
- mode != IN6_ADDR_GEN_MODE_NONE &&
- mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
- mode != IN6_ADDR_GEN_MODE_RANDOM)
+ if (check_addr_gen_mode(mode) < 0 ||
+ check_stable_privacy(idev, dev_net(dev), mode) < 0)
return -EINVAL;
- if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
- !idev->cnf.stable_secret.initialized &&
- !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized)
- return -EINVAL;
-
- idev->addr_gen_mode = mode;
+ idev->cnf.addr_gen_mode = mode;
err = 0;
}
@@ -5540,8 +5568,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
struct net_device *dev;
struct inet6_dev *idev;
- rcu_read_lock();
- for_each_netdev_rcu(net, dev) {
+ for_each_netdev(net, dev) {
idev = __in6_dev_get(dev);
if (idev) {
int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5550,7 +5577,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
dev_disable_change(idev);
}
}
- rcu_read_unlock();
}
static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
@@ -5645,6 +5671,47 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
return ret;
}
+static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret = 0;
+ int new_val;
+ struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1;
+ struct net *net = (struct net *)ctl->extra2;
+
+ ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+
+ if (write) {
+ new_val = *((int *)ctl->data);
+
+ if (check_addr_gen_mode(new_val) < 0)
+ return -EINVAL;
+
+ /* request for default */
+ if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) {
+ ipv6_devconf_dflt.addr_gen_mode = new_val;
+
+ /* request for individual net device */
+ } else {
+ if (!idev)
+ return ret;
+
+ if (check_stable_privacy(idev, net, new_val) < 0)
+ return -EINVAL;
+
+ if (idev->cnf.addr_gen_mode != new_val) {
+ idev->cnf.addr_gen_mode = new_val;
+ rtnl_lock();
+ addrconf_dev_config(idev->dev);
+ rtnl_unlock();
+ }
+ }
+ }
+
+ return ret;
+}
+
static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -5695,14 +5762,14 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
struct inet6_dev *idev = __in6_dev_get(dev);
if (idev) {
- idev->addr_gen_mode =
+ idev->cnf.addr_gen_mode =
IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
}
}
} else {
struct inet6_dev *idev = ctl->extra1;
- idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+ idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
}
out:
@@ -6090,6 +6157,13 @@ static const struct ctl_table addrconf_sysctl[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "addr_gen_mode",
+ .data = &ipv6_devconf.addr_gen_mode,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = addrconf_sysctl_addr_gen_mode,
+ },
+ {
/* sentinel */
}
};
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index aa42123bc301..04db40620ea6 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -302,7 +302,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
return -EINVAL;
snum = ntohs(addr->sin6_port);
- if (snum && snum < PROT_SOCK && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
+ if (snum && snum < inet_prot_sock(net) &&
+ !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
return -EACCES;
lock_sock(sk);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 189eb10b742d..dda6035e3b84 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -474,6 +474,9 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
int hdr_len = skb_network_header_len(skb);
int ah_hlen = (ah->hdrlen + 2) << 2;
+ if (err)
+ goto out;
+
work_iph = AH_SKB_CB(skb)->tmp;
auth_data = ah_tmp_auth(work_iph, hdr_len);
icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index cbcdd5db31f4..ff54faa75631 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -44,6 +44,8 @@
#include <net/protocol.h>
#include <linux/icmpv6.h>
+#include <linux/highmem.h>
+
struct esp_skb_cb {
struct xfrm_skb_cb xfrm;
void *tmp;
@@ -114,11 +116,40 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
__alignof__(struct scatterlist));
}
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+{
+ __be32 *seqhi;
+ struct crypto_aead *aead = x->data;
+ int seqhilen = 0;
+ u8 *iv;
+ struct aead_request *req;
+ struct scatterlist *sg;
+
+ 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);
+
+ /* Unref skb_frag_pages in the src scatterlist if necessary.
+ * Skip the first sg which comes from skb->data.
+ */
+ if (req->src != req->dst)
+ for (sg = sg_next(req->src); sg; sg = sg_next(sg))
+ put_page(sg_page(sg));
+}
+
static void esp_output_done(struct crypto_async_request *base, int err)
{
struct sk_buff *skb = base->data;
+ void *tmp;
+ struct dst_entry *dst = skb_dst(skb);
+ struct xfrm_state *x = dst->xfrm;
- kfree(ESP_SKB_CB(skb)->tmp);
+ tmp = ESP_SKB_CB(skb)->tmp;
+ esp_ssg_unref(x, tmp);
+ kfree(tmp);
xfrm_output_resume(skb, err);
}
@@ -138,6 +169,27 @@ static void esp_output_restore_header(struct sk_buff *skb)
esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
}
+static struct ip_esp_hdr *esp_output_set_esn(struct sk_buff *skb,
+ struct ip_esp_hdr *esph,
+ __be32 *seqhi)
+{
+ struct xfrm_state *x = skb_dst(skb)->xfrm;
+
+ /* 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);
+ }
+
+ esph->spi = x->id.spi;
+
+ return esph;
+}
+
static void esp_output_done_esn(struct crypto_async_request *base, int err)
{
struct sk_buff *skb = base->data;
@@ -146,14 +198,31 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
esp_output_done(base, err);
}
+static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
+{
+ /* Fill padding... */
+ if (tfclen) {
+ memset(tail, 0, tfclen);
+ tail += tfclen;
+ }
+ do {
+ int i;
+ for (i = 0; i < plen - 2; i++)
+ tail[i] = i + 1;
+ } while (0);
+ tail[plen - 2] = plen - 2;
+ tail[plen - 1] = proto;
+}
+
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_request *req;
- struct scatterlist *sg;
+ struct scatterlist *sg, *dsg;
struct sk_buff *trailer;
+ struct page *page;
void *tmp;
int blksize;
int clen;
@@ -164,10 +233,13 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
int nfrags;
int assoclen;
int seqhilen;
+ int tailen;
u8 *iv;
u8 *tail;
+ u8 *vaddr;
__be32 *seqhi;
__be64 seqno;
+ __u8 proto = *skb_mac_header(skb);
/* skb is pure payload to encrypt */
aead = x->data;
@@ -186,11 +258,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
blksize = ALIGN(crypto_aead_blocksize(aead), 4);
clen = ALIGN(skb->len + 2 + tfclen, blksize);
plen = clen - skb->len - tfclen;
-
- err = skb_cow_data(skb, tfclen + plen + alen, &trailer);
- if (err < 0)
- goto error;
- nfrags = err;
+ tailen = tfclen + plen + alen;
assoclen = sizeof(*esph);
seqhilen = 0;
@@ -200,59 +268,152 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
assoclen += seqhilen;
}
- tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
- if (!tmp) {
- err = -ENOMEM;
- goto error;
+ *skb_mac_header(skb) = IPPROTO_ESP;
+ esph = ip_esp_hdr(skb);
+
+ if (!skb_cloned(skb)) {
+ if (tailen <= skb_availroom(skb)) {
+ nfrags = 1;
+ trailer = skb;
+ tail = skb_tail_pointer(trailer);
+
+ goto skip_cow;
+ } else if ((skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS)
+ && !skb_has_frag_list(skb)) {
+ int allocsize;
+ struct sock *sk = skb->sk;
+ struct page_frag *pfrag = &x->xfrag;
+
+ allocsize = ALIGN(tailen, L1_CACHE_BYTES);
+
+ spin_lock_bh(&x->lock);
+
+ if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+ spin_unlock_bh(&x->lock);
+ goto cow;
+ }
+
+ page = pfrag->page;
+ get_page(page);
+
+ vaddr = kmap_atomic(page);
+
+ tail = vaddr + pfrag->offset;
+
+ esp_output_fill_trailer(tail, tfclen, plen, proto);
+
+ kunmap_atomic(vaddr);
+
+ nfrags = skb_shinfo(skb)->nr_frags;
+
+ __skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
+ tailen);
+ skb_shinfo(skb)->nr_frags = ++nfrags;
+
+ pfrag->offset = pfrag->offset + allocsize;
+ nfrags++;
+
+ skb->len += tailen;
+ skb->data_len += tailen;
+ skb->truesize += tailen;
+ if (sk)
+ atomic_add(tailen, &sk->sk_wmem_alloc);
+
+ skb_push(skb, -skb_network_offset(skb));
+
+ esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+ esph->spi = x->id.spi;
+
+ tmp = esp_alloc_tmp(aead, nfrags + 2, seqhilen);
+ if (!tmp) {
+ spin_unlock_bh(&x->lock);
+ err = -ENOMEM;
+ goto error;
+ }
+ seqhi = esp_tmp_seqhi(tmp);
+ iv = esp_tmp_iv(aead, tmp, seqhilen);
+ req = esp_tmp_req(aead, iv);
+ sg = esp_req_sg(aead, req);
+ dsg = &sg[nfrags];
+
+ esph = esp_output_set_esn(skb, esph, seqhi);
+
+ sg_init_table(sg, nfrags);
+ skb_to_sgvec(skb, sg,
+ (unsigned char *)esph - skb->data,
+ assoclen + ivlen + clen + alen);
+
+ allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
+
+ if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+ spin_unlock_bh(&x->lock);
+ err = -ENOMEM;
+ goto error;
+ }
+
+ skb_shinfo(skb)->nr_frags = 1;
+
+ page = pfrag->page;
+ get_page(page);
+ /* replace page frags in skb with new page */
+ __skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
+ pfrag->offset = pfrag->offset + allocsize;
+
+ sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
+ skb_to_sgvec(skb, dsg,
+ (unsigned char *)esph - skb->data,
+ assoclen + ivlen + clen + alen);
+
+ spin_unlock_bh(&x->lock);
+
+ goto skip_cow2;
+ }
}
- seqhi = esp_tmp_seqhi(tmp);
- iv = esp_tmp_iv(aead, tmp, seqhilen);
- req = esp_tmp_req(aead, iv);
- sg = esp_req_sg(aead, req);
+cow:
+ err = skb_cow_data(skb, tailen, &trailer);
+ if (err < 0)
+ goto error;
+ nfrags = err;
- /* Fill padding... */
tail = skb_tail_pointer(trailer);
- if (tfclen) {
- memset(tail, 0, tfclen);
- tail += tfclen;
- }
- do {
- int i;
- for (i = 0; i < plen - 2; i++)
- tail[i] = i + 1;
- } while (0);
- tail[plen - 2] = plen - 2;
- tail[plen - 1] = *skb_mac_header(skb);
- pskb_put(skb, trailer, clen - skb->len + alen);
+ esph = ip_esp_hdr(skb);
+skip_cow:
+ esp_output_fill_trailer(tail, tfclen, plen, proto);
+
+ pskb_put(skb, trailer, clen - skb->len + alen);
skb_push(skb, -skb_network_offset(skb));
- esph = ip_esp_hdr(skb);
- *skb_mac_header(skb) = IPPROTO_ESP;
esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+ esph->spi = x->id.spi;
- 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);
+ tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+ if (!tmp) {
+ err = -ENOMEM;
+ goto error;
}
- esph->spi = x->id.spi;
+ seqhi = esp_tmp_seqhi(tmp);
+ iv = esp_tmp_iv(aead, tmp, seqhilen);
+ req = esp_tmp_req(aead, iv);
+ sg = esp_req_sg(aead, req);
+ dsg = sg;
+
+ esph = esp_output_set_esn(skb, esph, seqhi);
sg_init_table(sg, nfrags);
skb_to_sgvec(skb, sg,
(unsigned char *)esph - skb->data,
assoclen + ivlen + clen + alen);
- aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+skip_cow2:
+ if ((x->props.flags & XFRM_STATE_ESN))
+ aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+ else
+ aead_request_set_callback(req, 0, esp_output_done, skb);
+
+ aead_request_set_crypt(req, sg, dsg, ivlen + clen, iv);
aead_request_set_ad(req, assoclen);
seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
@@ -278,6 +439,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
esp_output_restore_header(skb);
}
+ if (sg != dsg)
+ esp_ssg_unref(x, tmp);
kfree(tmp);
error:
@@ -343,6 +506,23 @@ static void esp_input_restore_header(struct sk_buff *skb)
__skb_pull(skb, 4);
}
+static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi)
+{
+ struct xfrm_state *x = xfrm_input_state(skb);
+ struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data;
+
+ /* 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)) {
+ esph = (void *)skb_push(skb, 4);
+ *seqhi = esph->spi;
+ esph->spi = esph->seq_no;
+ esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
+ }
+}
+
static void esp_input_done_esn(struct crypto_async_request *base, int err)
{
struct sk_buff *skb = base->data;
@@ -378,14 +558,6 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
goto out;
}
- nfrags = skb_cow_data(skb, 0, &trailer);
- if (nfrags < 0) {
- ret = -EINVAL;
- goto out;
- }
-
- ret = -ENOMEM;
-
assoclen = sizeof(*esph);
seqhilen = 0;
@@ -394,6 +566,27 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
assoclen += seqhilen;
}
+ if (!skb_cloned(skb)) {
+ if (!skb_is_nonlinear(skb)) {
+ nfrags = 1;
+
+ goto skip_cow;
+ } else if (!skb_has_frag_list(skb)) {
+ nfrags = skb_shinfo(skb)->nr_frags;
+ nfrags++;
+
+ goto skip_cow;
+ }
+ }
+
+ nfrags = skb_cow_data(skb, 0, &trailer);
+ if (nfrags < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+skip_cow:
+ ret = -ENOMEM;
tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
if (!tmp)
goto out;
@@ -404,26 +597,17 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
req = esp_tmp_req(aead, iv);
sg = esp_req_sg(aead, req);
- skb->ip_summed = CHECKSUM_NONE;
+ esp_input_set_header(skb, seqhi);
- esph = (struct ip_esp_hdr *)skb->data;
+ sg_init_table(sg, nfrags);
+ skb_to_sgvec(skb, sg, 0, skb->len);
- aead_request_set_callback(req, 0, esp_input_done, skb);
+ skb->ip_summed = CHECKSUM_NONE;
- /* 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)) {
- esph = (void *)skb_push(skb, 4);
- *seqhi = esph->spi;
- esph->spi = esph->seq_no;
- esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
+ if ((x->props.flags & XFRM_STATE_ESN))
aead_request_set_callback(req, 0, esp_input_done_esn, skb);
- }
-
- sg_init_table(sg, nfrags);
- skb_to_sgvec(skb, sg, 0, skb->len);
+ else
+ aead_request_set_callback(req, 0, esp_input_done, skb);
aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
aead_request_set_ad(req, assoclen);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 3036f665e6c8..230b5aac9f03 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -110,19 +110,17 @@ static const struct inet6_protocol icmpv6_protocol = {
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};
+/* Called with BH disabled */
static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
{
struct sock *sk;
- local_bh_disable();
-
sk = icmpv6_sk(net);
if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path (f.e. SIT or
* ip6ip6 tunnel) signals dst_link_failure() for an
* outgoing ICMP6 packet.
*/
- local_bh_enable();
return NULL;
}
return sk;
@@ -130,7 +128,7 @@ static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
{
- spin_unlock_bh(&sk->sk_lock.slock);
+ spin_unlock(&sk->sk_lock.slock);
}
/*
@@ -168,6 +166,30 @@ static bool is_ineligible(const struct sk_buff *skb)
return false;
}
+static bool icmpv6_mask_allow(int type)
+{
+ /* Informational messages are not limited. */
+ if (type & ICMPV6_INFOMSG_MASK)
+ return true;
+
+ /* Do not limit pmtu discovery, it would break it. */
+ if (type == ICMPV6_PKT_TOOBIG)
+ return true;
+
+ return false;
+}
+
+static bool icmpv6_global_allow(int type)
+{
+ if (icmpv6_mask_allow(type))
+ return true;
+
+ if (icmp_global_allow())
+ return true;
+
+ return false;
+}
+
/*
* Check the ICMP output rate limit
*/
@@ -178,12 +200,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
struct dst_entry *dst;
bool res = false;
- /* Informational messages are not limited. */
- if (type & ICMPV6_INFOMSG_MASK)
- return true;
-
- /* Do not limit pmtu discovery, it would break it. */
- if (type == ICMPV6_PKT_TOOBIG)
+ if (icmpv6_mask_allow(type))
return true;
/*
@@ -200,20 +217,16 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
} else {
struct rt6_info *rt = (struct rt6_info *)dst;
int tmo = net->ipv6.sysctl.icmpv6_time;
+ struct inet_peer *peer;
/* Give more bandwidth to wider prefixes. */
if (rt->rt6i_dst.plen < 128)
tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
- if (icmp_global_allow()) {
- struct inet_peer *peer;
-
- peer = inet_getpeer_v6(net->ipv6.peers,
- &fl6->daddr, 1);
- res = inet_peer_xrlim_allow(peer, tmo);
- if (peer)
- inet_putpeer(peer);
- }
+ peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr, 1);
+ res = inet_peer_xrlim_allow(peer, tmo);
+ if (peer)
+ inet_putpeer(peer);
}
dst_release(dst);
return res;
@@ -474,6 +487,13 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
return;
}
+ /* Needed by both icmp_global_allow and icmpv6_xmit_lock */
+ local_bh_disable();
+
+ /* Check global sysctl_icmp_msgs_per_sec ratelimit */
+ if (!icmpv6_global_allow(type))
+ goto out_bh_enable;
+
mip6_addr_swap(skb);
memset(&fl6, 0, sizeof(fl6));
@@ -492,7 +512,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
sk = icmpv6_xmit_lock(net);
if (!sk)
- return;
+ goto out_bh_enable;
+
sk->sk_mark = mark;
np = inet6_sk(sk);
@@ -552,6 +573,8 @@ out_dst_release:
dst_release(dst);
out:
icmpv6_xmit_unlock(sk);
+out_bh_enable:
+ local_bh_enable();
}
/* Slightly more convenient version of icmp6_send.
@@ -665,9 +688,10 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+ local_bh_disable();
sk = icmpv6_xmit_lock(net);
if (!sk)
- return;
+ goto out_bh_enable;
sk->sk_mark = mark;
np = inet6_sk(sk);
@@ -709,6 +733,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
dst_release(dst);
out:
icmpv6_xmit_unlock(sk);
+out_bh_enable:
+ local_bh_enable();
}
void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index a7bc54ab46e2..ce1aae4a7fc8 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -115,7 +115,7 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
[ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, },
};
-static int ila_build_state(struct net_device *dev, struct nlattr *nla,
+static int ila_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts)
{
@@ -238,6 +238,7 @@ static const struct lwtunnel_encap_ops ila_encap_ops = {
.fill_encap = ila_fill_encap_info,
.get_encap_size = ila_encap_nlsize,
.cmp_encap = ila_encap_cmp,
+ .owner = THIS_MODULE,
};
int ila_lwt_init(void)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 7396e75e161b..9a31d13bf180 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -28,46 +28,6 @@
#include <net/inet6_connection_sock.h>
#include <net/sock_reuseport.h>
-int inet6_csk_bind_conflict(const struct sock *sk,
- const struct inet_bind_bucket *tb, bool relax,
- bool reuseport_ok)
-{
- const struct sock *sk2;
- bool reuse = !!sk->sk_reuse;
- bool reuseport = !!sk->sk_reuseport && reuseport_ok;
- kuid_t uid = sock_i_uid((struct sock *)sk);
-
- /* We must walk the whole port owner list in this case. -DaveM */
- /*
- * See comment in inet_csk_bind_conflict about sock lookup
- * vs net namespaces issues.
- */
- sk_for_each_bound(sk2, &tb->owners) {
- if (sk != sk2 &&
- (!sk->sk_bound_dev_if ||
- !sk2->sk_bound_dev_if ||
- sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
- if ((!reuse || !sk2->sk_reuse ||
- sk2->sk_state == TCP_LISTEN) &&
- (!reuseport || !sk2->sk_reuseport ||
- rcu_access_pointer(sk->sk_reuseport_cb) ||
- (sk2->sk_state != TCP_TIME_WAIT &&
- !uid_eq(uid,
- sock_i_uid((struct sock *)sk2))))) {
- if (ipv6_rcv_saddr_equal(sk, sk2, true))
- break;
- }
- if (!relax && reuse && sk2->sk_reuse &&
- sk2->sk_state != TCP_LISTEN &&
- ipv6_rcv_saddr_equal(sk, sk2, true))
- break;
- }
- }
-
- return sk2 != NULL;
-}
-EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict);
-
struct dst_entry *inet6_csk_route_req(const struct sock *sk,
struct flowi6 *fl6,
const struct request_sock *req,
@@ -176,7 +136,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
/* Restore final destination back after routing done */
fl6.daddr = sk->sk_v6_daddr;
- res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt),
np->tclass);
rcu_read_unlock();
return res;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 02761c9fe43e..d0900918a19e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -268,54 +268,10 @@ int inet6_hash(struct sock *sk)
if (sk->sk_state != TCP_CLOSE) {
local_bh_disable();
- err = __inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
+ err = __inet_hash(sk, NULL);
local_bh_enable();
}
return err;
}
EXPORT_SYMBOL_GPL(inet6_hash);
-
-/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- * only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- * and 0.0.0.0 equals to 0.0.0.0 only
- */
-int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
- bool match_wildcard)
-{
- const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
- int sk2_ipv6only = inet_v6_ipv6only(sk2);
- int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
- int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
-
- /* if both are mapped, treat as IPv4 */
- if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
- if (!sk2_ipv6only) {
- if (sk->sk_rcv_saddr == sk2->sk_rcv_saddr)
- return 1;
- if (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr)
- return match_wildcard;
- }
- return 0;
- }
-
- if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
- return 1;
-
- if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
- !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
- return 1;
-
- if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
- !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED))
- return 1;
-
- if (sk2_rcv_saddr6 &&
- ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6))
- return 1;
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(ipv6_rcv_saddr_equal);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef5485204522..febde6c112bf 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -746,6 +746,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
u16 nlflags = NLM_F_EXCL;
int err;
+ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
+ nlflags |= NLM_F_APPEND;
+
ins = &fn->leaf;
for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 75b6108234dd..51b9835b3176 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -484,11 +484,6 @@ drop:
return 0;
}
-struct ipv6_tel_txoption {
- struct ipv6_txoptions ops;
- __u8 dst_opt[8];
-};
-
static int gre_handle_offloads(struct sk_buff *skb, bool csum)
{
return iptunnel_handle_offloads(skb,
@@ -582,6 +577,9 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
return -1;
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+ /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+ ipv6h = ipv6_hdr(skb);
+
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
@@ -998,6 +996,9 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
netif_keep_dst(dev);
+ /* This perm addr will be used as interface identifier by IPv6 */
+ dev->addr_assign_type = NET_ADDR_RANDOM;
+ eth_random_addr(dev->perm_addr);
}
static int ip6gre_tunnel_init_common(struct net_device *dev)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 89c59e656f44..fc7b4017ba24 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -191,6 +191,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
ops = rcu_dereference(inet6_offloads[proto]);
if (!ops || !ops->callbacks.gro_receive) {
__pskb_pull(skb, skb_gro_offset(skb));
+ skb_gro_frag0_invalidate(skb);
proto = ipv6_gso_pull_exthdrs(skb, proto);
skb_gro_pull(skb, -skb_transport_offset(skb));
skb_reset_transport_header(skb);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 70d0de404197..b6a94ff0bbd0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -172,7 +172,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
* which are using proper atomic operations or spinlocks.
*/
int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
- struct ipv6_txoptions *opt, int tclass)
+ __u32 mark, struct ipv6_txoptions *opt, int tclass)
{
struct net *net = sock_net(sk);
const struct ipv6_pinfo *np = inet6_sk(sk);
@@ -240,7 +240,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->mark = mark;
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
@@ -1344,7 +1344,7 @@ emsgsize:
*/
if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
headersize == sizeof(struct ipv6hdr) &&
- length < mtu - headersize &&
+ length <= mtu - headersize &&
!(flags & MSG_MORE) &&
rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
csummode = CHECKSUM_PARTIAL;
@@ -1373,7 +1373,7 @@ emsgsize:
*/
cork->length += length;
- if (((length > mtu) ||
+ if ((((length + fragheaderlen) > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 36d292180942..75fac933c209 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -400,18 +400,19 @@ ip6_tnl_dev_uninit(struct net_device *dev)
__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
{
- const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
- __u8 nexthdr = ipv6h->nexthdr;
- __u16 off = sizeof(*ipv6h);
+ const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
+ unsigned int nhoff = raw - skb->data;
+ unsigned int off = nhoff + sizeof(*ipv6h);
+ u8 next, nexthdr = ipv6h->nexthdr;
while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
- __u16 optlen = 0;
struct ipv6_opt_hdr *hdr;
- if (raw + off + sizeof(*hdr) > skb->data &&
- !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
+ u16 optlen;
+
+ if (!pskb_may_pull(skb, off + sizeof(*hdr)))
break;
- hdr = (struct ipv6_opt_hdr *) (raw + off);
+ hdr = (struct ipv6_opt_hdr *)(skb->data + off);
if (nexthdr == NEXTHDR_FRAGMENT) {
struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
if (frag_hdr->frag_off)
@@ -422,20 +423,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
} else {
optlen = ipv6_optlen(hdr);
}
+ /* cache hdr->nexthdr, since pskb_may_pull() might
+ * invalidate hdr
+ */
+ next = hdr->nexthdr;
if (nexthdr == NEXTHDR_DEST) {
- __u16 i = off + 2;
+ u16 i = 2;
+
+ /* Remember : hdr is no longer valid at this point. */
+ if (!pskb_may_pull(skb, off + optlen))
+ break;
+
while (1) {
struct ipv6_tlv_tnl_enc_lim *tel;
/* No more room for encapsulation limit */
- if (i + sizeof (*tel) > off + optlen)
+ if (i + sizeof(*tel) > optlen)
break;
- tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
+ tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
/* return index of option if found and valid */
if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
tel->length == 1)
- return i;
+ return i + off - nhoff;
/* else jump to next option */
if (tel->type)
i += tel->length + 2;
@@ -443,7 +453,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
i++;
}
}
- nexthdr = hdr->nexthdr;
+ nexthdr = next;
off += optlen;
}
return 0;
@@ -1108,7 +1118,7 @@ route_lookup:
t->parms.name);
goto tx_err_dst_release;
}
- mtu = dst_mtu(dst) - psh_hlen;
+ mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
@@ -1117,7 +1127,7 @@ route_lookup:
mtu = IPV6_MIN_MTU;
if (skb_dst(skb) && !t->parms.collect_md)
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
- if (skb->len > mtu && !skb_is_gso(skb)) {
+ if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
@@ -1303,6 +1313,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowlabel = key->label;
} else {
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+ /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+ ipv6h = ipv6_hdr(skb);
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index f4b4a4a5f4ba..c795fee372c4 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -49,6 +49,7 @@
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <linux/etherdevice.h>
#define IP6_VTI_HASH_SIZE_SHIFT 5
#define IP6_VTI_HASH_SIZE (1 << IP6_VTI_HASH_SIZE_SHIFT)
@@ -189,12 +190,12 @@ static int vti6_tnl_create2(struct net_device *dev)
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
int err;
+ dev->rtnl_link_ops = &vti6_link_ops;
err = register_netdevice(dev);
if (err < 0)
goto out;
strcpy(t->parms.name, dev->name);
- dev->rtnl_link_ops = &vti6_link_ops;
dev_hold(dev);
vti6_tnl_link(ip6n, t);
@@ -842,6 +843,9 @@ static void vti6_dev_setup(struct net_device *dev)
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
netif_keep_dst(dev);
+ /* This perm addr will be used as interface identifier by IPv6 */
+ dev->addr_assign_type = NET_ADDR_RANDOM;
+ eth_random_addr(dev->perm_addr);
}
/**
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 604d8953c775..babaf3ec2742 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2243,8 +2243,10 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
- if (c->mf6c_parent >= MAXMIFS)
+ if (c->mf6c_parent >= MAXMIFS) {
+ rtm->rtm_flags |= RTNH_F_UNRESOLVED;
return -ENOENT;
+ }
if (MIF_EXISTS(mrt, c->mf6c_parent) &&
nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0)
@@ -2286,7 +2288,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
}
int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
- int nowait, u32 portid)
+ u32 portid)
{
int err;
struct mr6_table *mrt;
@@ -2313,11 +2315,6 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
struct net_device *dev;
int vif;
- if (nowait) {
- read_unlock(&mrt_lock);
- return -EAGAIN;
- }
-
dev = skb->dev;
if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) {
read_unlock(&mrt_lock);
@@ -2355,7 +2352,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
return err;
}
- if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
+ if (rtm->rtm_flags & RTM_F_NOTIFY)
cache->mfc_flags |= MFC_NOTIFY;
err = __ip6mr_fill_mroute(mrt, skb, cache, rtm);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 14a3903f1c82..7139fffd61b6 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -81,7 +81,7 @@ static void mld_gq_timer_expire(unsigned long data);
static void mld_ifc_timer_expire(unsigned long data);
static void mld_ifc_event(struct inet6_dev *idev);
static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
-static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr);
+static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
static void mld_clear_delrec(struct inet6_dev *idev);
static bool mld_in_v1_mode(const struct inet6_dev *idev);
static int sf_setstate(struct ifmcaddr6 *pmc);
@@ -692,9 +692,9 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc)
dev_mc_del(dev, buf);
}
- if (mc->mca_flags & MAF_NOREPORT)
- goto done;
spin_unlock_bh(&mc->mca_lock);
+ if (mc->mca_flags & MAF_NOREPORT)
+ return;
if (!mc->idev->dead)
igmp6_leave_group(mc);
@@ -702,8 +702,6 @@ 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);
-done:
- ip6_mc_clear_src(mc);
spin_unlock_bh(&mc->mca_lock);
}
@@ -748,10 +746,11 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
spin_unlock_bh(&idev->mc_lock);
}
-static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
+static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
{
struct ifmcaddr6 *pmc, *pmc_prev;
- struct ip6_sf_list *psf, *psf_next;
+ struct ip6_sf_list *psf;
+ struct in6_addr *pmca = &im->mca_addr;
spin_lock_bh(&idev->mc_lock);
pmc_prev = NULL;
@@ -768,14 +767,20 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
}
spin_unlock_bh(&idev->mc_lock);
+ spin_lock_bh(&im->mca_lock);
if (pmc) {
- for (psf = pmc->mca_tomb; psf; psf = psf_next) {
- psf_next = psf->sf_next;
- kfree(psf);
+ im->idev = pmc->idev;
+ im->mca_crcount = idev->mc_qrv;
+ im->mca_sfmode = pmc->mca_sfmode;
+ if (pmc->mca_sfmode == MCAST_INCLUDE) {
+ im->mca_tomb = pmc->mca_tomb;
+ im->mca_sources = pmc->mca_sources;
+ for (psf = im->mca_sources; psf; psf = psf->sf_next)
+ psf->sf_crcount = im->mca_crcount;
}
in6_dev_put(pmc->idev);
- kfree(pmc);
}
+ spin_unlock_bh(&im->mca_lock);
}
static void mld_clear_delrec(struct inet6_dev *idev)
@@ -904,7 +909,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
mca_get(mc);
write_unlock_bh(&idev->lock);
- mld_del_delrec(idev, &mc->mca_addr);
+ mld_del_delrec(idev, mc);
igmp6_group_added(mc);
ma_put(mc);
return 0;
@@ -927,6 +932,7 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr)
write_unlock_bh(&idev->lock);
igmp6_group_dropped(ma);
+ ip6_mc_clear_src(ma);
ma_put(ma);
return 0;
@@ -2501,15 +2507,17 @@ void ipv6_mc_down(struct inet6_dev *idev)
/* Withdraw multicast list */
read_lock_bh(&idev->lock);
- mld_ifc_stop_timer(idev);
- mld_gq_stop_timer(idev);
- mld_dad_stop_timer(idev);
for (i = idev->mc_list; i; i = i->next)
igmp6_group_dropped(i);
- read_unlock_bh(&idev->lock);
- mld_clear_delrec(idev);
+ /* Should stop timer after group drop. or we will
+ * start timer again in mld_ifc_event()
+ */
+ mld_ifc_stop_timer(idev);
+ mld_gq_stop_timer(idev);
+ mld_dad_stop_timer(idev);
+ read_unlock_bh(&idev->lock);
}
static void ipv6_mc_reset(struct inet6_dev *idev)
@@ -2531,8 +2539,10 @@ void ipv6_mc_up(struct inet6_dev *idev)
read_lock_bh(&idev->lock);
ipv6_mc_reset(idev);
- for (i = idev->mc_list; i; i = i->next)
+ for (i = idev->mc_list; i; i = i->next) {
+ mld_del_delrec(idev, i);
igmp6_group_added(i);
+ }
read_unlock_bh(&idev->lock);
}
@@ -2565,6 +2575,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
/* Deactivate timers */
ipv6_mc_down(idev);
+ mld_clear_delrec(idev);
/* Delete all-nodes address. */
/* We cannot call ipv6_dev_mc_dec() directly, our caller in
@@ -2579,11 +2590,9 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
write_lock_bh(&idev->lock);
while ((i = idev->mc_list) != NULL) {
idev->mc_list = i->next;
- write_unlock_bh(&idev->lock);
- igmp6_group_dropped(i);
+ write_unlock_bh(&idev->lock);
ma_put(i);
-
write_lock_bh(&idev->lock);
}
write_unlock_bh(&idev->lock);
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index d5263dc364a9..b12e61b7b16c 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -72,10 +72,10 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
return ret;
}
-static bool rpfilter_is_local(const struct sk_buff *skb)
+static bool
+rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
{
- const struct rt6_info *rt = (const void *) skb_dst(skb);
- return rt && (rt->rt6i_flags & RTF_LOCAL);
+ return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
}
static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
struct ipv6hdr *iph;
bool invert = info->flags & XT_RPFILTER_INVERT;
- if (rpfilter_is_local(skb))
+ if (rpfilter_is_loopback(skb, xt_in(par)))
return true ^ invert;
iph = ipv6_hdr(skb);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 10090400c72f..eedee5d108d9 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -157,6 +157,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
@@ -180,6 +181,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
skb_dst_set(nskb, dst);
+ nskb->mark = fl6.flowi6_mark;
+
skb_reserve(nskb, hh_len + dst->header_len);
ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
ip6_dst_hoplimit(dst));
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c947aad8bcc6..765facf03d45 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -18,13 +18,6 @@
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
-static bool fib6_is_local(const struct sk_buff *skb)
-{
- const struct rt6_info *rt = (const void *)skb_dst(skb);
-
- return rt && (rt->rt6i_flags & RTF_LOCAL);
-}
-
static int get_ifindex(const struct net_device *dev)
{
return dev ? dev->ifindex : 0;
@@ -164,8 +157,10 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif);
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) {
- nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
+ nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
+ nft_fib_store_result(dest, priv->result, pkt,
+ nft_in(pkt)->ifindex);
return;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8417c41d8ec8..91eb3f7782dd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1464,7 +1464,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
struct fib6_node *fn;
/* Get the "current" route for this destination and
- * check if the redirect has come from approriate router.
+ * check if the redirect has come from appropriate router.
*
* RFC 4861 specifies that redirects should only be
* accepted if they come from the nexthop to the target.
@@ -1897,7 +1897,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
if (cfg->fc_encap) {
struct lwtunnel_state *lwtstate;
- err = lwtunnel_build_state(dev, cfg->fc_encap_type,
+ err = lwtunnel_build_state(cfg->fc_encap_type,
cfg->fc_encap, AF_INET6, cfg,
&lwtstate);
if (err)
@@ -2634,6 +2634,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
rt->dst.output = ip6_output;
rt->rt6i_idev = idev;
+ rt->rt6i_protocol = RTPROT_KERNEL;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
if (anycast)
rt->rt6i_flags |= RTF_ANYCAST;
@@ -2711,13 +2712,16 @@ struct arg_dev_net {
struct net *net;
};
+/* called with write lock held for table with rt */
static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
const struct arg_dev_net *adn = arg;
const struct net_device *dev = adn->dev;
if ((rt->dst.dev == dev || !dev) &&
- rt != adn->net->ipv6.ip6_null_entry)
+ rt != adn->net->ipv6.ip6_null_entry &&
+ (rt->rt6i_nsiblings == 0 ||
+ !rt->rt6i_idev->cnf.ignore_routes_with_linkdown))
return -1;
return 0;
@@ -2768,7 +2772,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
old MTU is the lowest MTU in the path, update the route PMTU
to reflect the increase. In this case if the other nodes' MTU
also have the lowest MTU, TOO BIG MESSAGE will be lead to
- PMTU discouvery.
+ PMTU discovery.
*/
if (rt->dst.dev == arg->dev &&
dst_metric_raw(&rt->dst, RTAX_MTU) &&
@@ -2896,6 +2900,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[RTA_MULTIPATH]) {
cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+
+ err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
+ cfg->fc_mp_len);
+ if (err < 0)
+ goto errout;
}
if (tb[RTA_PREF]) {
@@ -2909,9 +2918,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[RTA_ENCAP])
cfg->fc_encap = tb[RTA_ENCAP];
- if (tb[RTA_ENCAP_TYPE])
+ 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);
+ if (err < 0)
+ goto errout;
+ }
+
if (tb[RTA_EXPIRES]) {
unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ);
@@ -3169,7 +3183,7 @@ static int rt6_fill_node(struct net *net,
struct sk_buff *skb, struct rt6_info *rt,
struct in6_addr *dst, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
- int prefix, int nowait, unsigned int flags)
+ unsigned int flags)
{
u32 metrics[RTAX_MAX];
struct rtmsg *rtm;
@@ -3177,13 +3191,6 @@ static int rt6_fill_node(struct net *net,
long expires;
u32 table;
- if (prefix) { /* user wants prefix routes only */
- if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
- /* success since this is not a prefix route */
- return 1;
- }
- }
-
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
if (!nlh)
return -EMSGSIZE;
@@ -3223,7 +3230,7 @@ static int rt6_fill_node(struct net *net,
else
rtm->rtm_type = RTN_UNICAST;
rtm->rtm_flags = 0;
- if (!netif_carrier_ok(rt->dst.dev)) {
+ if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
rtm->rtm_flags |= RTNH_F_LINKDOWN;
if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
rtm->rtm_flags |= RTNH_F_DEAD;
@@ -3261,19 +3268,12 @@ static int rt6_fill_node(struct net *net,
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
- int err = ip6mr_get_route(net, skb, rtm, nowait,
- portid);
-
- if (err <= 0) {
- if (!nowait) {
- if (err == 0)
- return 0;
- goto nla_put_failure;
- } else {
- if (err == -EMSGSIZE)
- goto nla_put_failure;
- }
- }
+ int err = ip6mr_get_route(net, skb, rtm, portid);
+
+ if (err == 0)
+ return 0;
+ if (err < 0)
+ goto nla_put_failure;
} else
#endif
if (nla_put_u32(skb, RTA_IIF, iif))
@@ -3317,7 +3317,8 @@ static int rt6_fill_node(struct net *net,
if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
goto nla_put_failure;
- lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+ if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+ goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
@@ -3330,18 +3331,26 @@ nla_put_failure:
int rt6_dump_route(struct rt6_info *rt, void *p_arg)
{
struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
- int prefix;
+ struct net *net = arg->net;
+
+ if (rt == net->ipv6.ip6_null_entry)
+ return 0;
if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
struct rtmsg *rtm = nlmsg_data(arg->cb->nlh);
- prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0;
- } else
- prefix = 0;
- return rt6_fill_node(arg->net,
+ /* user wants prefix routes only */
+ if (rtm->rtm_flags & RTM_F_PREFIX &&
+ !(rt->rt6i_flags & RTF_PREFIX_RT)) {
+ /* success since this is not a prefix route */
+ return 1;
+ }
+ }
+
+ return rt6_fill_node(net,
arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
- prefix, 0, NLM_F_MULTI);
+ NLM_F_MULTI);
}
static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
@@ -3422,17 +3431,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
goto errout;
}
- /* Reserve room for dummy headers, this skb can pass
- through good chunk of routing engine.
- */
- skb_reset_mac_header(skb);
- skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
-
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, 0, 0);
+ nlh->nlmsg_seq, 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -3459,7 +3462,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
goto errout;
err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
- event, info->portid, seq, 0, 0, nlm_flags);
+ event, info->portid, seq, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index b172d85c650a..a855eb325b03 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -176,6 +176,8 @@ static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info)
val = nla_data(info->attrs[SEG6_ATTR_DST]);
t_new = kmemdup(val, sizeof(*val), GFP_KERNEL);
+ if (!t_new)
+ return -ENOMEM;
mutex_lock(&sdata->lock);
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index ef1c8a46e7ac..b274f1d95e03 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -45,7 +45,7 @@
#include <net/seg6_hmac.h>
#include <linux/random.h>
-static char * __percpu *hmac_ring;
+static DEFINE_PER_CPU(char [SEG6_HMAC_RING_SIZE], hmac_ring);
static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
{
@@ -192,7 +192,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
*/
local_bh_disable();
- ring = *this_cpu_ptr(hmac_ring);
+ ring = this_cpu_ptr(hmac_ring);
off = ring;
/* source address */
@@ -353,27 +353,6 @@ out:
}
EXPORT_SYMBOL(seg6_push_hmac);
-static int seg6_hmac_init_ring(void)
-{
- int i;
-
- hmac_ring = alloc_percpu(char *);
-
- if (!hmac_ring)
- return -ENOMEM;
-
- for_each_possible_cpu(i) {
- char *ring = kzalloc(SEG6_HMAC_RING_SIZE, GFP_KERNEL);
-
- if (!ring)
- return -ENOMEM;
-
- *per_cpu_ptr(hmac_ring, i) = ring;
- }
-
- return 0;
-}
-
static int seg6_hmac_init_algo(void)
{
struct seg6_hmac_algo *algo;
@@ -400,7 +379,7 @@ static int seg6_hmac_init_algo(void)
*p_tfm = tfm;
}
- p_tfm = this_cpu_ptr(algo->tfms);
+ p_tfm = raw_cpu_ptr(algo->tfms);
tfm = *p_tfm;
shsize = sizeof(*shash) + crypto_shash_descsize(tfm);
@@ -410,7 +389,8 @@ static int seg6_hmac_init_algo(void)
return -ENOMEM;
for_each_possible_cpu(cpu) {
- shash = kzalloc(shsize, GFP_KERNEL);
+ shash = kzalloc_node(shsize, GFP_KERNEL,
+ cpu_to_node(cpu));
if (!shash)
return -ENOMEM;
*per_cpu_ptr(algo->shashs, cpu) = shash;
@@ -422,16 +402,7 @@ static int seg6_hmac_init_algo(void)
int __init seg6_hmac_init(void)
{
- int ret;
-
- ret = seg6_hmac_init_ring();
- if (ret < 0)
- goto out;
-
- ret = seg6_hmac_init_algo();
-
-out:
- return ret;
+ return seg6_hmac_init_algo();
}
EXPORT_SYMBOL(seg6_hmac_init);
@@ -450,13 +421,6 @@ void seg6_hmac_exit(void)
struct seg6_hmac_algo *algo = NULL;
int i, alg_count, cpu;
- for_each_possible_cpu(i) {
- char *ring = *per_cpu_ptr(hmac_ring, i);
-
- kfree(ring);
- }
- free_percpu(hmac_ring);
-
alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
for (i = 0; i < alg_count; i++) {
algo = &hmac_algos[i];
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index bbfca22c34ae..6124e159c882 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -265,7 +265,9 @@ int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
#ifdef CONFIG_DST_CACHE
+ preempt_disable();
dst = dst_cache_get(&slwt->cache);
+ preempt_enable();
#endif
if (unlikely(!dst)) {
@@ -286,7 +288,9 @@ int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
}
#ifdef CONFIG_DST_CACHE
+ preempt_disable();
dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+ preempt_enable();
#endif
}
@@ -299,7 +303,7 @@ drop:
return err;
}
-static int seg6_build_state(struct net_device *dev, struct nlattr *nla,
+static int seg6_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts)
{
@@ -418,6 +422,7 @@ static const struct lwtunnel_encap_ops seg6_iptun_ops = {
.fill_encap = seg6_fill_encap_info,
.get_encap_size = seg6_encap_nlsize,
.cmp_encap = seg6_encap_cmp,
+ .owner = THIS_MODULE,
};
int __init seg6_iptunnel_init(void)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index a4d49760bf43..895ff650db43 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -16,7 +16,7 @@
#include <linux/tcp.h>
#include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
#include <linux/kernel.h>
#include <net/ipv6.h>
#include <net/tcp.h>
@@ -24,7 +24,7 @@
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
-static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie6_secret[2] __read_mostly;
/* RFC 2460, Section 8.3:
* [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
@@ -41,30 +41,27 @@ static __u16 const msstab[] = {
9000 - 60,
};
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch);
-
-static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
+static u32 cookie_hash(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
__be16 sport, __be16 dport, u32 count, int c)
{
- __u32 *tmp;
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 count;
+ __be16 sport;
+ __be16 dport;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *saddr,
+ .daddr = *daddr,
+ .count = count,
+ .sport = sport,
+ .dport = dport
+ };
net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
-
- tmp = this_cpu_ptr(ipv6_cookie_scratch);
-
- /*
- * we have 320 bits of information to hash, copy in the remaining
- * 192 bits required for sha_transform, from the syncookie6_secret
- * and overwrite the digest with the secret
- */
- memcpy(tmp + 10, syncookie6_secret[c], 44);
- memcpy(tmp, saddr, 16);
- memcpy(tmp + 4, daddr, 16);
- tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
- tmp[9] = count;
- sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
- return tmp[17];
+ return siphash(&combined, offsetofend(typeof(combined), dport),
+ &syncookie6_secret[c]);
}
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a4cdf6a34c30..6b9fc63fd4d2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -287,6 +287,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
inet->inet_dport,
&tp->tsoffset);
+ if (tcp_fastopen_defer_connect(sk, &err))
+ return err;
+ if (err)
+ goto late_failure;
+
err = tcp_connect(sk);
if (err)
goto late_failure;
@@ -295,7 +300,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
late_failure:
tcp_set_state(sk, TCP_CLOSE);
- __sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
@@ -470,7 +474,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, opt, np->tclass);
+ err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -841,7 +845,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
- ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass);
+ ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -1143,10 +1147,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
tcp_ca_openreq_child(newsk, dst);
tcp_sync_mss(newsk, dst_mtu(dst));
- newtp->advmss = dst_metric_advmss(dst);
- if (tcp_sk(sk)->rx_opt.user_mss &&
- tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
- newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+ newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
tcp_initialize_rcv_mss(newsk);
@@ -1621,7 +1622,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
- .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
@@ -1652,7 +1652,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
- .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
@@ -1745,7 +1744,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
srcp = ntohs(inet->inet_sport);
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
- icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
@@ -1889,6 +1888,7 @@ struct proto tcpv6_prot = {
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
+ .keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4d5c4eee4b3f..b4c6516a3a0c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -55,6 +55,16 @@
#include <trace/events/skb.h>
#include "udp_impl.h"
+static bool udp6_lib_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if defined(CONFIG_NET_L3_MASTER_DEV)
+ if (!net->ipv4.sysctl_udp_l3mdev_accept &&
+ skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
+ return true;
+#endif
+ return false;
+}
+
static u32 udp6_ehashfn(const struct net *net,
const struct in6_addr *laddr,
const u16 lport,
@@ -103,7 +113,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
- return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
+ return udp_lib_get_port(sk, snum, hash2_nulladdr);
}
static void udp_v6_rehash(struct sock *sk)
@@ -118,7 +128,7 @@ static void udp_v6_rehash(struct sock *sk)
static int compute_score(struct sock *sk, struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned short hnum,
- int dif)
+ int dif, bool exact_dif)
{
int score;
struct inet_sock *inet;
@@ -149,7 +159,7 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if || exact_dif) {
if (sk->sk_bound_dev_if != dif)
return -1;
score++;
@@ -165,7 +175,7 @@ static int compute_score(struct sock *sk, struct net *net,
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned int hnum, int dif,
- struct udp_hslot *hslot2,
+ bool exact_dif, struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
@@ -176,7 +186,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
score = compute_score(sk, net, saddr, sport,
- daddr, hnum, dif);
+ daddr, hnum, dif, exact_dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
@@ -212,6 +222,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
unsigned short hnum = ntohs(dport);
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+ bool exact_dif = udp6_lib_exact_dif_match(net, skb);
int score, badness, matches = 0, reuseport = 0;
u32 hash = 0;
@@ -223,7 +234,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
goto begin;
result = udp6_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif,
+ daddr, hnum, dif, exact_dif,
hslot2, skb);
if (!result) {
unsigned int old_slot2 = slot2;
@@ -239,7 +250,8 @@ struct sock *__udp6_lib_lookup(struct net *net,
result = udp6_lib_lookup2(net, saddr, sport,
daddr, hnum, dif,
- hslot2, skb);
+ exact_dif, hslot2,
+ skb);
}
return result;
}
@@ -247,7 +259,8 @@ begin:
result = NULL;
badness = -1;
sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, saddr, sport, daddr, hnum, dif);
+ score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
+ exact_dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-12 13:51:28 +0000