aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c84
-rw-r--r--net/core/dst.c2
-rw-r--r--net/core/fib_rules.c2
-rw-r--r--net/core/neighbour.c11
-rw-r--r--net/core/netpoll.c169
-rw-r--r--net/core/pktgen.c10
-rw-r--r--net/core/rtnetlink.c4
-rw-r--r--net/core/sock.c10
8 files changed, 187 insertions, 105 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index f9aa699ab6cb..94c1eeed25e5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1448,13 +1448,10 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
if (skb->len > (dev->mtu + dev->hard_header_len))
return NET_RX_DROP;
- skb_dst_drop(skb);
+ skb_set_dev(skb, dev);
skb->tstamp.tv64 = 0;
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, dev);
- skb->mark = 0;
- secpath_reset(skb);
- nf_reset(skb);
return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1614,6 +1611,36 @@ static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
return false;
}
+/**
+ * skb_dev_set -- assign a new device to a buffer
+ * @skb: buffer for the new device
+ * @dev: network device
+ *
+ * If an skb is owned by a device already, we have to reset
+ * all data private to the namespace a device belongs to
+ * before assigning it a new device.
+ */
+#ifdef CONFIG_NET_NS
+void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
+{
+ skb_dst_drop(skb);
+ if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
+ secpath_reset(skb);
+ nf_reset(skb);
+ skb_init_secmark(skb);
+ skb->mark = 0;
+ skb->priority = 0;
+ skb->nf_trace = 0;
+ skb->ipvs_property = 0;
+#ifdef CONFIG_NET_SCHED
+ skb->tc_index = 0;
+#endif
+ }
+ skb->dev = dev;
+}
+EXPORT_SYMBOL(skb_set_dev);
+#endif /* CONFIG_NET_NS */
+
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
@@ -1982,6 +2009,21 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
return rc;
}
+/*
+ * Returns true if either:
+ * 1. skb has frag_list and the device doesn't support FRAGLIST, or
+ * 2. skb is fragmented and the device does not support SG, or if
+ * at least one of fragments is in highmem and device does not
+ * support DMA from it.
+ */
+static inline int skb_needs_linearize(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
+ (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
+ illegal_highdma(dev, skb)));
+}
+
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
@@ -2018,18 +2060,8 @@ int dev_queue_xmit(struct sk_buff *skb)
if (netif_needs_gso(dev, skb))
goto gso;
- if (skb_has_frags(skb) &&
- !(dev->features & NETIF_F_FRAGLIST) &&
- __skb_linearize(skb))
- goto out_kfree_skb;
-
- /* Fragmented skb is linearized if device does not support SG,
- * or if at least one of fragments is in highmem and device
- * does not support DMA from it.
- */
- if (skb_shinfo(skb)->nr_frags &&
- (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
- __skb_linearize(skb))
+ /* Convert a paged skb to linear, if required */
+ if (skb_needs_linearize(skb, dev) && __skb_linearize(skb))
goto out_kfree_skb;
/* If packet is not checksummed and device does not support
@@ -2430,6 +2462,7 @@ int netif_receive_skb(struct sk_buff *skb)
struct packet_type *ptype, *pt_prev;
struct net_device *orig_dev;
struct net_device *null_or_orig;
+ struct net_device *null_or_bond;
int ret = NET_RX_DROP;
__be16 type;
@@ -2500,21 +2533,19 @@ ncls:
* bonding interfaces still make their way to any base bonding
* device that may have registered for a specific ptype. The
* handler may have to adjust skb->dev and orig_dev.
- *
- * null_or_orig can be overloaded since it will not be set when
- * using VLANs on top of bonding. Putting it here prevents
- * disturbing the ptype_all handlers above.
*/
+ null_or_bond = NULL;
if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
(vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
- null_or_orig = vlan_dev_real_dev(skb->dev);
+ null_or_bond = vlan_dev_real_dev(skb->dev);
}
type = skb->protocol;
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
if (ptype->type == type && (ptype->dev == null_or_orig ||
- ptype->dev == skb->dev || ptype->dev == orig_dev)) {
+ ptype->dev == skb->dev || ptype->dev == orig_dev ||
+ ptype->dev == null_or_bond)) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
@@ -2583,7 +2614,7 @@ out:
return netif_receive_skb(skb);
}
-void napi_gro_flush(struct napi_struct *napi)
+static void napi_gro_flush(struct napi_struct *napi)
{
struct sk_buff *skb, *next;
@@ -2596,7 +2627,6 @@ void napi_gro_flush(struct napi_struct *napi)
napi->gro_count = 0;
napi->gro_list = NULL;
}
-EXPORT_SYMBOL(napi_gro_flush);
enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
@@ -3207,7 +3237,7 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
const struct net_device_stats *stats = dev_get_stats(dev);
- seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+ seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
dev->name, stats->rx_bytes, stats->rx_packets,
stats->rx_errors,
@@ -3662,10 +3692,10 @@ void __dev_set_rx_mode(struct net_device *dev)
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
*/
- if (dev->uc.count > 0 && !dev->uc_promisc) {
+ if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
__dev_set_promiscuity(dev, 1);
dev->uc_promisc = 1;
- } else if (dev->uc.count == 0 && dev->uc_promisc) {
+ } else if (netdev_uc_empty(dev) && dev->uc_promisc) {
__dev_set_promiscuity(dev, -1);
dev->uc_promisc = 0;
}
diff --git a/net/core/dst.c b/net/core/dst.c
index 57bc4d5b8d08..cb1b3488b739 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -17,6 +17,7 @@
#include <linux/string.h>
#include <linux/types.h>
#include <net/net_namespace.h>
+#include <linux/sched.h>
#include <net/dst.h>
@@ -79,6 +80,7 @@ loop:
while ((dst = next) != NULL) {
next = dst->next;
prefetch(&next->next);
+ cond_resched();
if (likely(atomic_read(&dst->__refcnt))) {
last->next = dst;
last = dst;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 02a3b2c69c1e..9a24377146bf 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -708,7 +708,7 @@ static struct notifier_block fib_rules_notifier = {
.notifier_call = fib_rules_event,
};
-static int fib_rules_net_init(struct net *net)
+static int __net_init fib_rules_net_init(struct net *net)
{
INIT_LIST_HEAD(&net->rules_ops);
spin_lock_init(&net->rules_mod_lock);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f35377b643e4..f2efd72da799 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2417,8 +2417,7 @@ EXPORT_SYMBOL(neigh_seq_stop);
static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct proc_dir_entry *pde = seq->private;
- struct neigh_table *tbl = pde->data;
+ struct neigh_table *tbl = seq->private;
int cpu;
if (*pos == 0)
@@ -2435,8 +2434,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct proc_dir_entry *pde = seq->private;
- struct neigh_table *tbl = pde->data;
+ struct neigh_table *tbl = seq->private;
int cpu;
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
@@ -2455,8 +2453,7 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v)
static int neigh_stat_seq_show(struct seq_file *seq, void *v)
{
- struct proc_dir_entry *pde = seq->private;
- struct neigh_table *tbl = pde->data;
+ struct neigh_table *tbl = seq->private;
struct neigh_statistics *st = v;
if (v == SEQ_START_TOKEN) {
@@ -2501,7 +2498,7 @@ static int neigh_stat_seq_open(struct inode *inode, struct file *file)
if (!ret) {
struct seq_file *sf = file->private_data;
- sf->private = PDE(inode);
+ sf->private = PDE(inode)->data;
}
return ret;
};
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 0b4d0d35ef40..7aa697253765 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -407,11 +407,24 @@ static void arp_reply(struct sk_buff *skb)
__be32 sip, tip;
unsigned char *sha;
struct sk_buff *send_skb;
- struct netpoll *np = NULL;
+ struct netpoll *np, *tmp;
+ unsigned long flags;
+ int hits = 0;
+
+ if (list_empty(&npinfo->rx_np))
+ return;
+
+ /* Before checking the packet, we do some early
+ inspection whether this is interesting at all */
+ spin_lock_irqsave(&npinfo->rx_lock, flags);
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (np->dev == skb->dev)
+ hits++;
+ }
+ spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- if (npinfo->rx_np && npinfo->rx_np->dev == skb->dev)
- np = npinfo->rx_np;
- if (!np)
+ /* No netpoll struct is using this dev */
+ if (!hits)
return;
/* No arp on this interface */
@@ -437,77 +450,91 @@ static void arp_reply(struct sk_buff *skb)
arp_ptr += skb->dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
- /* if we actually cared about dst hw addr, it would get copied here */
+ /* If we actually cared about dst hw addr,
+ it would get copied here */
arp_ptr += skb->dev->addr_len;
memcpy(&tip, arp_ptr, 4);
/* Should we ignore arp? */
- if (tip != np->local_ip ||
- ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
+ if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
return;
size = arp_hdr_len(skb->dev);
- send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
- LL_RESERVED_SPACE(np->dev));
- if (!send_skb)
- return;
-
- skb_reset_network_header(send_skb);
- arp = (struct arphdr *) skb_put(send_skb, size);
- send_skb->dev = skb->dev;
- send_skb->protocol = htons(ETH_P_ARP);
+ spin_lock_irqsave(&npinfo->rx_lock, flags);
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (tip != np->local_ip)
+ continue;
- /* Fill the device header for the ARP frame */
- if (dev_hard_header(send_skb, skb->dev, ptype,
- sha, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- return;
- }
+ send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
+ LL_RESERVED_SPACE(np->dev));
+ if (!send_skb)
+ continue;
- /*
- * Fill out the arp protocol part.
- *
- * we only support ethernet device type,
- * which (according to RFC 1390) should always equal 1 (Ethernet).
- */
+ skb_reset_network_header(send_skb);
+ arp = (struct arphdr *) skb_put(send_skb, size);
+ send_skb->dev = skb->dev;
+ send_skb->protocol = htons(ETH_P_ARP);
- arp->ar_hrd = htons(np->dev->type);
- arp->ar_pro = htons(ETH_P_IP);
- arp->ar_hln = np->dev->addr_len;
- arp->ar_pln = 4;
- arp->ar_op = htons(type);
+ /* Fill the device header for the ARP frame */
+ if (dev_hard_header(send_skb, skb->dev, ptype,
+ sha, np->dev->dev_addr,
+ send_skb->len) < 0) {
+ kfree_skb(send_skb);
+ continue;
+ }
- arp_ptr=(unsigned char *)(arp + 1);
- memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &tip, 4);
- arp_ptr += 4;
- memcpy(arp_ptr, sha, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &sip, 4);
+ /*
+ * Fill out the arp protocol part.
+ *
+ * we only support ethernet device type,
+ * which (according to RFC 1390) should
+ * always equal 1 (Ethernet).
+ */
- netpoll_send_skb(np, send_skb);
+ arp->ar_hrd = htons(np->dev->type);
+ arp->ar_pro = htons(ETH_P_IP);
+ arp->ar_hln = np->dev->addr_len;
+ arp->ar_pln = 4;
+ arp->ar_op = htons(type);
+
+ arp_ptr = (unsigned char *)(arp + 1);
+ memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
+ arp_ptr += np->dev->addr_len;
+ memcpy(arp_ptr, &tip, 4);
+ arp_ptr += 4;
+ memcpy(arp_ptr, sha, np->dev->addr_len);
+ arp_ptr += np->dev->addr_len;
+ memcpy(arp_ptr, &sip, 4);
+
+ netpoll_send_skb(np, send_skb);
+
+ /* If there are several rx_hooks for the same address,
+ we're fine by sending a single reply */
+ break;
+ }
+ spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
int __netpoll_rx(struct sk_buff *skb)
{
int proto, len, ulen;
+ int hits = 0;
struct iphdr *iph;
struct udphdr *uh;
- struct netpoll_info *npi = skb->dev->npinfo;
- struct netpoll *np = npi->rx_np;
+ struct netpoll_info *npinfo = skb->dev->npinfo;
+ struct netpoll *np, *tmp;
- if (!np)
+ if (list_empty(&npinfo->rx_np))
goto out;
+
if (skb->dev->type != ARPHRD_ETHER)
goto out;
/* check if netpoll clients need ARP */
if (skb->protocol == htons(ETH_P_ARP) &&
atomic_read(&trapped)) {
- skb_queue_tail(&npi->arp_tx, skb);
+ skb_queue_tail(&npinfo->arp_tx, skb);
return 1;
}
@@ -551,16 +578,23 @@ int __netpoll_rx(struct sk_buff *skb)
goto out;
if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
goto out;
- if (np->local_ip && np->local_ip != iph->daddr)
- goto out;
- if (np->remote_ip && np->remote_ip != iph->saddr)
- goto out;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- goto out;
- np->rx_hook(np, ntohs(uh->source),
- (char *)(uh+1),
- ulen - sizeof(struct udphdr));
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (np->local_ip && np->local_ip != iph->daddr)
+ continue;
+ if (np->remote_ip && np->remote_ip != iph->saddr)
+ continue;
+ if (np->local_port && np->local_port != ntohs(uh->dest))
+ continue;
+
+ np->rx_hook(np, ntohs(uh->source),
+ (char *)(uh+1),
+ ulen - sizeof(struct udphdr));
+ hits++;
+ }
+
+ if (!hits)
+ goto out;
kfree_skb(skb);
return 1;
@@ -684,6 +718,7 @@ int netpoll_setup(struct netpoll *np)
struct net_device *ndev = NULL;
struct in_device *in_dev;
struct netpoll_info *npinfo;
+ struct netpoll *npe, *tmp;
unsigned long flags;
int err;
@@ -704,7 +739,7 @@ int netpoll_setup(struct netpoll *np)
}
npinfo->rx_flags = 0;
- npinfo->rx_np = NULL;
+ INIT_LIST_HEAD(&npinfo->rx_np);
spin_lock_init(&npinfo->rx_lock);
skb_queue_head_init(&npinfo->arp_tx);
@@ -785,7 +820,7 @@ int netpoll_setup(struct netpoll *np)
if (np->rx_hook) {
spin_lock_irqsave(&npinfo->rx_lock, flags);
npinfo->rx_flags |= NETPOLL_RX_ENABLED;
- npinfo->rx_np = np;
+ list_add_tail(&np->rx, &npinfo->rx_np);
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
@@ -801,9 +836,16 @@ int netpoll_setup(struct netpoll *np)
return 0;
release:
- if (!ndev->npinfo)
+ if (!ndev->npinfo) {
+ spin_lock_irqsave(&npinfo->rx_lock, flags);
+ list_for_each_entry_safe(npe, tmp, &npinfo->rx_np, rx) {
+ npe->dev = NULL;
+ }
+ spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+
kfree(npinfo);
- np->dev = NULL;
+ }
+
dev_put(ndev);
return err;
}
@@ -823,10 +865,11 @@ void netpoll_cleanup(struct netpoll *np)
if (np->dev) {
npinfo = np->dev->npinfo;
if (npinfo) {
- if (npinfo->rx_np == np) {
+ if (!list_empty(&npinfo->rx_np)) {
spin_lock_irqsave(&npinfo->rx_lock, flags);
- npinfo->rx_np = NULL;
- npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
+ list_del(&np->rx);
+ if (list_empty(&npinfo->rx_np))
+ npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index a23b45f08ec9..2e692afdc55d 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -250,8 +250,7 @@ struct pktgen_dev {
__u64 count; /* Default No packets to send */
__u64 sofar; /* How many pkts we've sent so far */
__u64 tx_bytes; /* How many bytes we've transmitted */
- __u64 errors; /* Errors when trying to transmit,
- pkts will be re-sent */
+ __u64 errors; /* Errors when trying to transmit, */
/* runtime counters relating to clone_skb */
@@ -3465,6 +3464,12 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
pkt_dev->seq_num++;
pkt_dev->tx_bytes += pkt_dev->last_pkt_size;
break;
+ case NET_XMIT_DROP:
+ case NET_XMIT_CN:
+ case NET_XMIT_POLICED:
+ /* skb has been consumed */
+ pkt_dev->errors++;
+ break;
default: /* Drivers are not supposed to return other values! */
if (net_ratelimit())
pr_info("pktgen: %s xmit error: %d\n",
@@ -3519,6 +3524,7 @@ static int pktgen_thread_worker(void *arg)
wait_event_interruptible_timeout(t->queue,
t->control != 0,
HZ/10);
+ try_to_freeze();
continue;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 794bcb897ff0..62f3878a6010 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1386,7 +1386,7 @@ static struct notifier_block rtnetlink_dev_notifier = {
};
-static int rtnetlink_net_init(struct net *net)
+static int __net_init rtnetlink_net_init(struct net *net)
{
struct sock *sk;
sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX,
@@ -1397,7 +1397,7 @@ static int rtnetlink_net_init(struct net *net)
return 0;
}
-static void rtnetlink_net_exit(struct net *net)
+static void __net_exit rtnetlink_net_exit(struct net *net)
{
netlink_kernel_release(net->rtnl);
net->rtnl = NULL;
diff --git a/net/core/sock.c b/net/core/sock.c
index 76ff58d43e26..ceef50bd131b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -741,7 +741,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
struct timeval tm;
} v;
- unsigned int lv = sizeof(int);
+ int lv = sizeof(int);
int len;
if (get_user(len, optlen))
@@ -1205,6 +1205,10 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
if (newsk->sk_prot->sockets_allocated)
percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+
+ if (sock_flag(newsk, SOCK_TIMESTAMP) ||
+ sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE))
+ net_enable_timestamp();
}
out:
return newsk;
@@ -2136,13 +2140,13 @@ int sock_prot_inuse_get(struct net *net, struct proto *prot)
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
-static int sock_inuse_init_net(struct net *net)
+static int __net_init sock_inuse_init_net(struct net *net)
{
net->core.inuse = alloc_percpu(struct prot_inuse);
return net->core.inuse ? 0 : -ENOMEM;
}
-static void sock_inuse_exit_net(struct net *net)
+static void __net_exit sock_inuse_exit_net(struct net *net)
{
free_percpu(net->core.inuse);
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.