aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile2
-rw-r--r--net/core/dev.c12
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/flow.c38
-rw-r--r--net/core/link_watch.c2
-rw-r--r--net/core/neighbour.c8
-rw-r--r--net/core/netpoll.c4
-rw-r--r--net/core/pktgen.c8
-rw-r--r--net/core/scm.c2
-rw-r--r--net/core/secure_seq.c184
-rw-r--r--net/core/skbuff.c39
11 files changed, 267 insertions, 36 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 8a04dd22cf77..0d357b1c4e57 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -3,7 +3,7 @@
#
obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
- gen_stats.o gen_estimator.o net_namespace.o
+ gen_stats.o gen_estimator.o net_namespace.o secure_seq.o
obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 9444c5cb4137..b10ff0a71855 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1515,6 +1515,14 @@ static inline bool is_skb_forwardable(struct net_device *dev,
*/
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+ if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
+ atomic_long_inc(&dev->rx_dropped);
+ kfree_skb(skb);
+ return NET_RX_DROP;
+ }
+ }
+
skb_orphan(skb);
nf_reset(skb);
@@ -4497,10 +4505,10 @@ void __dev_set_rx_mode(struct net_device *dev)
*/
if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
__dev_set_promiscuity(dev, 1);
- dev->uc_promisc = 1;
+ dev->uc_promisc = true;
} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
__dev_set_promiscuity(dev, -1);
- dev->uc_promisc = 0;
+ dev->uc_promisc = false;
}
if (ops->ndo_set_multicast_list)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index e7ab0c0285b5..3231b468bb72 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -384,8 +384,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
*/
list_for_each_entry(r, &ops->rules_list, list) {
if (r->action == FR_ACT_GOTO &&
- r->target == rule->pref) {
- BUG_ON(rtnl_dereference(r->ctarget) != NULL);
+ r->target == rule->pref &&
+ rtnl_dereference(r->ctarget) == NULL) {
rcu_assign_pointer(r->ctarget, rule);
if (--ops->unresolved_rules == 0)
break;
diff --git a/net/core/flow.c b/net/core/flow.c
index 990703b8863b..555a456efb07 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -22,7 +22,7 @@
#include <linux/cpumask.h>
#include <linux/mutex.h>
#include <net/flow.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <linux/security.h>
struct flow_cache_entry {
@@ -30,6 +30,7 @@ struct flow_cache_entry {
struct hlist_node hlist;
struct list_head gc_list;
} u;
+ struct net *net;
u16 family;
u8 dir;
u32 genid;
@@ -172,29 +173,26 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
static u32 flow_hash_code(struct flow_cache *fc,
struct flow_cache_percpu *fcp,
- const struct flowi *key)
+ const struct flowi *key,
+ size_t keysize)
{
const u32 *k = (const u32 *) key;
+ const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
- return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd)
+ return jhash2(k, length, fcp->hash_rnd)
& (flow_cache_hash_size(fc) - 1);
}
-typedef unsigned long flow_compare_t;
-
/* I hear what you're saying, use memcmp. But memcmp cannot make
- * important assumptions that we can here, such as alignment and
- * constant size.
+ * important assumptions that we can here, such as alignment.
*/
-static int flow_key_compare(const struct flowi *key1, const struct flowi *key2)
+static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
+ size_t keysize)
{
const flow_compare_t *k1, *k1_lim, *k2;
- const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t);
-
- BUILD_BUG_ON(sizeof(struct flowi) % sizeof(flow_compare_t));
k1 = (const flow_compare_t *) key1;
- k1_lim = k1 + n_elem;
+ k1_lim = k1 + keysize;
k2 = (const flow_compare_t *) key2;
@@ -215,6 +213,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
struct flow_cache_entry *fle, *tfle;
struct hlist_node *entry;
struct flow_cache_object *flo;
+ size_t keysize;
unsigned int hash;
local_bh_disable();
@@ -222,6 +221,11 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
fle = NULL;
flo = NULL;
+
+ keysize = flow_key_size(family);
+ if (!keysize)
+ goto nocache;
+
/* Packet really early in init? Making flow_cache_init a
* pre-smp initcall would solve this. --RR */
if (!fcp->hash_table)
@@ -230,11 +234,12 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
if (fcp->hash_rnd_recalc)
flow_new_hash_rnd(fc, fcp);
- hash = flow_hash_code(fc, fcp, key);
+ hash = flow_hash_code(fc, fcp, key, keysize);
hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) {
- if (tfle->family == family &&
+ if (tfle->net == net &&
+ tfle->family == family &&
tfle->dir == dir &&
- flow_key_compare(key, &tfle->key) == 0) {
+ flow_key_compare(key, &tfle->key, keysize) == 0) {
fle = tfle;
break;
}
@@ -246,9 +251,10 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
if (fle) {
+ fle->net = net;
fle->family = family;
fle->dir = dir;
- memcpy(&fle->key, key, sizeof(*key));
+ memcpy(&fle->key, key, keysize * sizeof(flow_compare_t));
fle->object = NULL;
hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
fcp->hash_count++;
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index a7b342131869..357bd4ee4baa 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -126,7 +126,7 @@ static void linkwatch_schedule_work(int urgent)
return;
/* It's already running which is good enough. */
- if (!cancel_delayed_work(&linkwatch_work))
+ if (!__cancel_delayed_work(&linkwatch_work))
return;
/* Otherwise we reschedule it again for immediate execution. */
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8fab9b0bb203..1334d7e56f02 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1319,11 +1319,15 @@ static void neigh_proxy_process(unsigned long arg)
if (tdif <= 0) {
struct net_device *dev = skb->dev;
+
__skb_unlink(skb, &tbl->proxy_queue);
- if (tbl->proxy_redo && netif_running(dev))
+ if (tbl->proxy_redo && netif_running(dev)) {
+ rcu_read_lock();
tbl->proxy_redo(skb);
- else
+ rcu_read_unlock();
+ } else {
kfree_skb(skb);
+ }
dev_put(dev);
} else if (!sched_next || tdif < sched_next)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index adf84dd8c7b5..52622517e0d8 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -558,13 +558,14 @@ int __netpoll_rx(struct sk_buff *skb)
if (skb_shared(skb))
goto out;
- iph = (struct iphdr *)skb->data;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out;
+ iph = (struct iphdr *)skb->data;
if (iph->ihl < 5 || iph->version != 4)
goto out;
if (!pskb_may_pull(skb, iph->ihl*4))
goto out;
+ iph = (struct iphdr *)skb->data;
if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
goto out;
@@ -579,6 +580,7 @@ int __netpoll_rx(struct sk_buff *skb)
if (pskb_trim_rcsum(skb, len))
goto out;
+ iph = (struct iphdr *)skb->data;
if (iph->protocol != IPPROTO_UDP)
goto out;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f76079cd750c..e35a6fbb8110 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1070,7 +1070,9 @@ static ssize_t pktgen_if_write(struct file *file,
len = num_arg(&user_buffer[i], 10, &value);
if (len < 0)
return len;
-
+ if ((value > 0) &&
+ (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+ return -ENOTSUPP;
i += len;
pkt_dev->clone_skb = value;
@@ -3555,7 +3557,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
pkt_dev->min_pkt_size = ETH_ZLEN;
pkt_dev->max_pkt_size = ETH_ZLEN;
pkt_dev->nfrags = 0;
- pkt_dev->clone_skb = pg_clone_skb_d;
pkt_dev->delay = pg_delay_d;
pkt_dev->count = pg_count_d;
pkt_dev->sofar = 0;
@@ -3563,7 +3564,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
pkt_dev->udp_src_max = 9;
pkt_dev->udp_dst_min = 9;
pkt_dev->udp_dst_max = 9;
-
pkt_dev->vlan_p = 0;
pkt_dev->vlan_cfi = 0;
pkt_dev->vlan_id = 0xffff;
@@ -3575,6 +3575,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
err = pktgen_setup_dev(pkt_dev, ifname);
if (err)
goto out1;
+ if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)
+ pkt_dev->clone_skb = pg_clone_skb_d;
pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir,
&pktgen_if_fops, pkt_dev);
diff --git a/net/core/scm.c b/net/core/scm.c
index 4c1ef026d695..811b53fb330e 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -192,7 +192,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
goto error;
cred->uid = cred->euid = p->creds.uid;
- cred->gid = cred->egid = p->creds.uid;
+ cred->gid = cred->egid = p->creds.gid;
put_cred(p->cred);
p->cred = cred;
}
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
new file mode 100644
index 000000000000..45329d7c9dd9
--- /dev/null
+++ b/net/core/secure_seq.c
@@ -0,0 +1,184 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/cryptohash.h>
+#include <linux/module.h>
+#include <linux/cache.h>
+#include <linux/random.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
+#include <linux/string.h>
+
+#include <net/secure_seq.h>
+
+static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+
+static int __init net_secret_init(void)
+{
+ get_random_bytes(net_secret, sizeof(net_secret));
+ return 0;
+}
+late_initcall(net_secret_init);
+
+static u32 seq_scale(u32 seq)
+{
+ /*
+ * As close as possible to RFC 793, which
+ * suggests using a 250 kHz clock.
+ * Further reading shows this assumes 2 Mb/s networks.
+ * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate.
+ * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but
+ * we also need to limit the resolution so that the u32 seq
+ * overlaps less than one time per MSL (2 minutes).
+ * Choosing a clock of 64 ns period is OK. (period of 274 s)
+ */
+ return seq + (ktime_to_ns(ktime_get_real()) >> 6);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 secret[MD5_MESSAGE_BYTES / 4];
+ u32 hash[MD5_DIGEST_WORDS];
+ u32 i;
+
+ memcpy(hash, saddr, 16);
+ for (i = 0; i < 4; i++)
+ secret[i] = net_secret[i] + daddr[i];
+ secret[4] = net_secret[4] +
+ (((__force u16)sport << 16) + (__force u16)dport);
+ for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+ secret[i] = net_secret[i];
+
+ md5_transform(hash, secret);
+
+ return seq_scale(hash[0]);
+}
+EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+
+u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
+ __be16 dport)
+{
+ u32 secret[MD5_MESSAGE_BYTES / 4];
+ u32 hash[MD5_DIGEST_WORDS];
+ u32 i;
+
+ memcpy(hash, saddr, 16);
+ for (i = 0; i < 4; i++)
+ secret[i] = net_secret[i] + (__force u32) daddr[i];
+ secret[4] = net_secret[4] + (__force u32)dport;
+ for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+ secret[i] = net_secret[i];
+
+ md5_transform(hash, secret);
+
+ return hash[0];
+}
+#endif
+
+#ifdef CONFIG_INET
+__u32 secure_ip_id(__be32 daddr)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+
+ hash[0] = (__force __u32) daddr;
+ hash[1] = net_secret[13];
+ hash[2] = net_secret[14];
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ return hash[0];
+}
+
+__u32 secure_ipv6_id(const __be32 daddr[4])
+{
+ __u32 hash[4];
+
+ memcpy(hash, daddr, 16);
+ md5_transform(hash, net_secret);
+
+ return hash[0];
+}
+
+__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+
+ hash[0] = (__force u32)saddr;
+ hash[1] = (__force u32)daddr;
+ hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ return seq_scale(hash[0]);
+}
+
+u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+
+ hash[0] = (__force u32)saddr;
+ hash[1] = (__force u32)daddr;
+ hash[2] = (__force u32)dport ^ net_secret[14];
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ return hash[0];
+}
+EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
+#endif
+
+#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
+u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+ u64 seq;
+
+ hash[0] = (__force u32)saddr;
+ hash[1] = (__force u32)daddr;
+ hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ seq = hash[0] | (((u64)hash[1]) << 32);
+ seq += ktime_to_ns(ktime_get_real());
+ seq &= (1ull << 48) - 1;
+
+ return seq;
+}
+EXPORT_SYMBOL(secure_dccp_sequence_number);
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 secret[MD5_MESSAGE_BYTES / 4];
+ u32 hash[MD5_DIGEST_WORDS];
+ u64 seq;
+ u32 i;
+
+ memcpy(hash, saddr, 16);
+ for (i = 0; i < 4; i++)
+ secret[i] = net_secret[i] + daddr[i];
+ secret[4] = net_secret[4] +
+ (((__force u16)sport << 16) + (__force u16)dport);
+ for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+ secret[i] = net_secret[i];
+
+ md5_transform(hash, secret);
+
+ seq = hash[0] | (((u64)hash[1]) << 32);
+ seq += ktime_to_ns(ktime_get_real());
+ seq &= (1ull << 48) - 1;
+
+ return seq;
+}
+EXPORT_SYMBOL(secure_dccpv6_sequence_number);
+#endif
+#endif
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2beda824636e..387703f56fce 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -611,8 +611,21 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
}
EXPORT_SYMBOL_GPL(skb_morph);
-/* skb frags copy userspace buffers to kernel */
-static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
+/* skb_copy_ubufs - copy userspace skb frags buffers to kernel
+ * @skb: the skb to modify
+ * @gfp_mask: allocation priority
+ *
+ * This must be called on SKBTX_DEV_ZEROCOPY skb.
+ * It will copy all frags into kernel and drop the reference
+ * to userspace pages.
+ *
+ * If this function is called from an interrupt gfp_mask() must be
+ * %GFP_ATOMIC.
+ *
+ * Returns 0 on success or a negative error code on failure
+ * to allocate kernel memory to copy to.
+ */
+int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
{
int i;
int num_frags = skb_shinfo(skb)->nr_frags;
@@ -652,6 +665,8 @@ static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
skb_shinfo(skb)->frags[i - 1].page = head;
head = (struct page *)head->private;
}
+
+ skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
return 0;
}
@@ -677,7 +692,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, gfp_mask))
return NULL;
- skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
}
n = skb + 1;
@@ -803,7 +817,6 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
n = NULL;
goto out;
}
- skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
@@ -896,7 +909,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, gfp_mask))
goto nofrags;
- skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
get_page(skb_shinfo(skb)->frags[i].page);
@@ -1369,8 +1381,21 @@ pull_pages:
}
EXPORT_SYMBOL(__pskb_pull_tail);
-/* Copy some data bits from skb to kernel buffer. */
-
+/**
+ * skb_copy_bits - copy bits from skb to kernel buffer
+ * @skb: source skb
+ * @offset: offset in source
+ * @to: destination buffer
+ * @len: number of bytes to copy
+ *
+ * Copy the specified number of bytes from the source skb to the
+ * destination buffer.
+ *
+ * CAUTION ! :
+ * If its prototype is ever changed,
+ * check arch/{*}/net/{*}.S files,
+ * since it is called from BPF assembly code.
+ */
int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
int start = skb_headlen(skb);
generated by cgit (git 2.34.1) at 2025-06-02 05:12:27 +0000